Paper Citation Record · LEDGER

Verbalizable Representations Form a Global Workspace in Language Models

As of 23 August 2026, this Paper Citation Record lists 100 of 181 outbound references and 6 inbound Pith citation observations for arXiv:2607.15495.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.15495 v1

Coverage vector

measured 100 of 181 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T23:15:29.682340Z

measured 106 of 106 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:17:56.777542Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T05:33:56.166169Z

Reference resolution

100 of 181 outbound references displayed

verified exact3
verified fuzzy0
unresolved94
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1c7e8897-a9ae-4881-8261-f62f5908b6b5 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Verbalizable Representations Form a Global Workspace in Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:16.405392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2c520cf-724a-4378-b4c5-c7460a261116 · outbound

This paper cites Integrated information theory (iit) 4.0: Formulating the properties of phenomenal exis- tence in physical terms.PLoS computational biology, 19(10):e1011465, 2023.

Verbalizable Representations Form a Global Workspace in Language Models Integrated information theory (iit) 4.0: Formulating the properties of phenomenal exis- tence in physical terms.PLoS computational biology, 19(10):e1011465, 2023

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:16.507879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9787ad3-f8ad-4841-a8e9-eed183f90667 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:16.610947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 284b0fab-8d0e-47e6-97ee-65f74fa91f24 · outbound

This paper cites Claude opus 4.5 system card.

Verbalizable Representations Form a Global Workspace in Language Models Claude opus 4.5 system card

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:16.677888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6bf80f5-ff10-4560-819c-f70bc179541b · outbound

This paper cites Claude sonnet 4.5 system card.

Verbalizable Representations Form a Global Workspace in Language Models Claude sonnet 4.5 system card

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:16.811534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c1a8d5d-0ebb-4395-b305-fe10671f7f36 · outbound

This paper cites Refusal in language models is mediated by a single direction.Advances in Neural Information Processing Systems, 37:136037–136083,.

Verbalizable Representations Form a Global Workspace in Language Models Refusal in language models is mediated by a single direction.Advances in Neural Information Processing Systems, 37:136037–136083,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:16.922011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af5e420-5b87-4ea0-8292-b4105b511c96 · outbound

This paper cites Language Model Circuits Are Sparse in the Neuron Basis.

Verbalizable Representations Form a Global Workspace in Language Models Language Model Circuits Are Sparse in the Neuron Basis

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.151999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2eb563a-9507-407a-be94-9bb246b62697 · outbound

This paper cites Tensorlens: End-to-end transformer analysis via high-order attention tensors.arXiv preprint arXiv:2601.17958, 2026.

Verbalizable Representations Form a Global Workspace in Language Models Tensorlens: End-to-end transformer analysis via high-order attention tensors.arXiv preprint arXiv:2601.17958, 2026

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.298913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671153ab-ac3b-462e-a9c0-876edc9d88a8 · outbound

This paper cites Using Fast Weights to Attend to the Recent Past.

Verbalizable Representations Form a Global Workspace in Language Models Using Fast Weights to Attend to the Recent Past

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.446424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9854bc1d-223f-49f5-ae10-b456b7da7c6c · outbound

This paper cites Cambridge University Press, Cam- bridge, 1988.

Verbalizable Representations Form a Global Workspace in Language Models Cambridge University Press, Cam- bridge, 1988

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.542620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636c51d0-ae72-4aab-b8c5-2f394758223e · outbound

This paper cites Working memory: looking back and looking forward.Nature Reviews Neu- roscience, 4(10):829–839, 2003.

Verbalizable Representations Form a Global Workspace in Language Models Working memory: looking back and looking forward.Nature Reviews Neu- roscience, 4(10):829–839, 2003

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.680765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a29b537-f74b-409b-ae58-091a5dacfec5 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Verbalizable Representations Form a Global Workspace in Language Models Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.824580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0a8cca2-1ff5-481a-8ab7-8b22179902e0 · outbound

This paper cites The Consciousness Prior.

Verbalizable Representations Form a Global Workspace in Language Models The Consciousness Prior

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:17.967153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaf8d18d-17ee-44ac-b72c-9cfc3db6e356 · outbound

This paper cites Taken out of context: On measuring situational awareness in LLMs.

Verbalizable Representations Form a Global Workspace in Language Models Taken out of context: On measuring situational awareness in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.089120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57bc6d85-c289-495b-ad03-e8e8bc3323b7 · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

Verbalizable Representations Form a Global Workspace in Language Models Tell me about yourself: LLMs are aware of their learned behaviors

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.170826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc229df1-4dc5-4fc1-a42a-57af21c62e80 · outbound

This paper cites Language models can explain neu- rons in language models, 2023.

Verbalizable Representations Form a Global Workspace in Language Models Language models can explain neu- rons in language models, 2023

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.326980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e354eae5-30fa-43bf-a1c7-00604cc20572 · outbound

This paper cites Looking Inward: Language Models Can Learn About Themselves by Introspection.

Verbalizable Representations Form a Global Workspace in Language Models Looking Inward: Language Models Can Learn About Themselves by Introspection

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.474238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5afac6bc-e33d-4814-aee3-9ed244a5c8c8 · outbound

This paper cites On a confusion about a function of consciousness.Behavioral and Brain Sci- ences, 18(2):227–247, 1995.

Verbalizable Representations Form a Global Workspace in Language Models On a confusion about a function of consciousness.Behavioral and Brain Sci- ences, 18(2):227–247, 1995

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.545015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c9c298-bf8f-4e01-a480-6324eac72c71 · outbound

This paper cites Gradient pursuits.IEEE Transactions on Signal Processing, 56(6):2370–2382, 2008.

Verbalizable Representations Form a Global Workspace in Language Models Gradient pursuits.IEEE Transactions on Signal Processing, 56(6):2370–2382, 2008

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.610565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cceac6-59c2-4b7b-b3a7-b1c64741ea6e · outbound

This paper cites Slot Machines: How LLMs Keep Track of Multiple Entities.

Verbalizable Representations Form a Global Workspace in Language Models Slot Machines: How LLMs Keep Track of Multiple Entities

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.699660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f57dc7f-32a1-4ff0-bd50-6efd9175201c · outbound

This paper cites Towards monosemanticity: Decom- posing language models with dictionary learning.Transformer Circuits Thread, 2023.

Verbalizable Representations Form a Global Workspace in Language Models Towards monosemanticity: Decom- posing language models with dictionary learning.Transformer Circuits Thread, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.796058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32123543-4b1d-427d-8359-bc2db27f8b33 · outbound

This paper cites Consciousness in Artificial Intelligence: Insights from the Science of Consciousness.

Verbalizable Representations Form a Global Workspace in Language Models Consciousness in Artificial Intelligence: Insights from the Science of Consciousness

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:18.867284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fa2c11e-a680-4453-987f-cb9077461988 · outbound

This paper cites Could a Large Language Model be Conscious?.

Verbalizable Representations Form a Global Workspace in Language Models Could a Large Language Model be Conscious?

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.025474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b3f4aa1-d1b2-49c5-899b-7680e5dae93c · outbound

This paper cites Oxford University Press New York, 1996.

Verbalizable Representations Form a Global Workspace in Language Models Oxford University Press New York, 1996

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.097494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0c355e5-3e6c-4c9d-b9f9-7fce70dbdad6 · outbound

This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoencoders.arXiv preprint arXiv:2409.14507, 2024.

Verbalizable Representations Form a Global Workspace in Language Models A is for absorption: Studying feature splitting and absorption in sparse autoencoders.arXiv preprint arXiv:2409.14507, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.192570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1973f5a3-a744-4e2d-8728-63df377402b6 · outbound

This paper cites SelfIE: Self-Interpretation of Large Language Model Embeddings.

Verbalizable Representations Form a Global Workspace in Language Models SelfIE: Self-Interpretation of Large Language Model Embeddings

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.338403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb728837-592f-421a-9d35-1552900828f2 · outbound

This paper cites DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models.

Verbalizable Representations Form a Global Workspace in Language Models DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.464490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faa74bfe-a12b-4126-8123-f6dc64b3edfb · outbound

This paper cites Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs.

Verbalizable Representations Form a Global Workspace in Language Models Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.566197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04accae1-5f6d-4f7a-b929-9aa8052779be · outbound

This paper cites A taxonomy of external and internal attention.Annual Review of Psychology, 62:73–101, 2011.

Verbalizable Representations Form a Global Workspace in Language Models A taxonomy of external and internal attention.Annual Review of Psychology, 62:73–101, 2011

Reference 29

Resolution: malformed identifier; no resolver link, observed 2026-08-01T23:15:19.634634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb0d9d1-5b8c-4098-9ce1-e571fd0050ff · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Verbalizable Representations Form a Global Workspace in Language Models Training Verifiers to Solve Math Word Problems

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.741734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f08f9533-0327-41f3-bea9-20d2096ba61c · outbound

This paper cites Does It Make Sense to Speak of Introspection in Large Language Models?.

Verbalizable Representations Form a Global Workspace in Language Models Does It Make Sense to Speak of Introspection in Large Language Models?

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:19.845541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f00299a-dcef-4344-9d84-b215bab28a84 · outbound

This paper cites The magical number 4 in short-term memory: A reconsideration of men- tal storage capacity.Behavioral and Brain Sciences, 24(1):87–114, 2001.

Verbalizable Representations Form a Global Workspace in Language Models The magical number 4 in short-term memory: A reconsideration of men- tal storage capacity.Behavioral and Brain Sciences, 24(1):87–114, 2001

Reference 32

Resolution: malformed identifier; no resolver link, observed 2026-08-01T23:15:19.936599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6d236b3-abc9-480d-8da2-bc0bec8e797d · outbound

This paper cites Analyzing transformers in em- bedding space.

Verbalizable Representations Form a Global Workspace in Language Models Analyzing transformers in em- bedding space

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.172382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce83c46-f01d-4737-bfe9-8f49f4236762 · outbound

This paper cites Experimental and theoretical approaches to conscious processing.Neuron, 70(2):200–227, 2011.

Verbalizable Representations Form a Global Workspace in Language Models Experimental and theoretical approaches to conscious processing.Neuron, 70(2):200–227, 2011

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.327748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46121054-ca91-408a-a7c0-626689169e2a · outbound

This paper cites Towards a cognitive neuroscience of consciousness: basic evidence and a workspace framework.Cognition, 79(1–2):1–37, 2001.

Verbalizable Representations Form a Global Workspace in Language Models Towards a cognitive neuroscience of consciousness: basic evidence and a workspace framework.Cognition, 79(1–2):1–37, 2001

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.378843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd6eedc7-878d-4189-b1ef-a221b2fd7dae · outbound

This paper cites doi: 10.18653/v1/2023.acl-long.893.

Verbalizable Representations Form a Global Workspace in Language Models doi: 10.18653/v1/2023.acl-long.893

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.265653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c79a2d-5be0-4b42-b2ac-229c62c82e41 · outbound

This paper cites What is consciousness, and could ma- chines have it?Science, 358(6362):486–492, 2017.

Verbalizable Representations Form a Global Workspace in Language Models What is consciousness, and could ma- chines have it?Science, 358(6362):486–492, 2017

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.537121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b7447b-6196-427c-b4e7-26f209fea0e1 · outbound

This paper cites From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step.

Verbalizable Representations Form a Global Workspace in Language Models From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.584455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8d990d6-672b-49d2-8aaf-b5af20bbec24 · outbound

This paper cites A neuronal model of a global workspace in effortful cognitive tasks.Proceedings of the National Academy of Sci- ences, 95(24):14529–14534, 1998.

Verbalizable Representations Form a Global Workspace in Language Models A neuronal model of a global workspace in effortful cognitive tasks.Proceedings of the National Academy of Sci- ences, 95(24):14529–14534, 1998

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.463430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bde276d-0ef0-470a-a123-9551844da32e · outbound

This paper cites Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals.

Verbalizable Representations Form a Global Workspace in Language Models Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.714051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7e0295e-79cd-4650-8c5c-2ba936403446 · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread, 2021.

Verbalizable Representations Form a Global Workspace in Language Models A mathematical framework for transformer circuits.Transformer Circuits Thread, 2021

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.773855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 914133ed-5878-495d-985e-60fd8a0ad5e6 · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Verbalizable Representations Form a Global Workspace in Language Models Transcoders Find Interpretable LLM Feature Circuits

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.650998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3db9c6d-9563-4c9b-8aa9-dff212a6c40c · outbound

This paper cites Unsupervised decoding of encoded reasoning using language model inter- pretability.arXiv preprint arXiv:2512.01222, 2025.

Verbalizable Representations Form a Global Workspace in Language Models Unsupervised decoding of encoded reasoning using language model inter- pretability.arXiv preprint arXiv:2512.01222, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.913972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c53517b6-9a9a-4432-b51b-4944b896f9a2 · outbound

This paper cites Computational higher-order theories of consciousness.

Verbalizable Representations Form a Global Workspace in Language Models Computational higher-order theories of consciousness

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.958912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f5528ad-7111-479d-b55d-4a929ae02e6d · outbound

This paper cites Toy models of superposition.Transformer Circuits Thread, 2022.

Verbalizable Representations Form a Global Workspace in Language Models Toy models of superposition.Transformer Circuits Thread, 2022

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:20.843039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8b13074-ce29-4594-ad8d-71030c51a747 · outbound

This paper cites From Simulation to Enaction: Post-trained language models recognize and react to their own generations.

Verbalizable Representations Form a Global Workspace in Language Models From Simulation to Enaction: Post-trained language models recognize and react to their own generations

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:21.143225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4e43cd-e271-4d55-9f71-0e478c24c85f · outbound

This paper cites Gaze heads: How VLMs look at what they describe.

Verbalizable Representations Form a Global Workspace in Language Models Gaze heads: How VLMs look at what they describe

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:21.284492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6350b635-0191-4b41-80dc-e347b910b7d9 · outbound

This paper cites Natural language autoencoders produce unsupervised explanations of llm activations.Transformer Circuits Thread, 2026.

Verbalizable Representations Form a Global Workspace in Language Models Natural language autoencoders produce unsupervised explanations of llm activations.Transformer Circuits Thread, 2026

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:21.024292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68d3786-c7f1-40da-8452-cb8ad91c4fda · outbound

This paper cites The benefits of bad advice: Autocontrastive decoding across model layers.

Verbalizable Representations Form a Global Workspace in Language Models The benefits of bad advice: Autocontrastive decoding across model layers

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:21.633318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff5b980e-8894-43c9-956a-f3129be9799b · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Verbalizable Representations Form a Global Workspace in Language Models Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:21.840407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15905d18-feab-48cb-bb8c-1d6fa837c316 · outbound

This paper cites Automatically Identifying Local and Global Circuits with Linear Computation Graphs.

Verbalizable Representations Form a Global Workspace in Language Models Automatically Identifying Local and Global Circuits with Linear Computation Graphs

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:21.461651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e10fd95-add3-48e1-81c3-3a833a5a45e2 · outbound

This paper cites Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models.

Verbalizable Representations Form a Global Workspace in Language Models Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:22.360923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb8e2d2e-4ced-4890-8a5f-a7c93cdadad3 · outbound

This paper cites Equivalent linear mappings of large language models.arXiv preprint arXiv:2505.24293, 2025.

Verbalizable Representations Form a Global Workspace in Language Models Equivalent linear mappings of large language models.arXiv preprint arXiv:2505.24293, 2025

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:22.555875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b21322c-689b-4c91-9106-7e7355592ac2 · outbound

This paper cites Dissecting Recall of Factual Associations in Auto-Regressive Language Models.

Verbalizable Representations Form a Global Workspace in Language Models Dissecting Recall of Factual Associations in Auto-Regressive Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:22.194747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90126bb1-5e24-4770-9338-bdc44c54de10 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 57

Resolution: malformed identifier; no resolver link, observed 2026-08-01T23:15:23.166361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d406d612-cdeb-4712-a465-bb94445022c3 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Verbalizable Representations Form a Global Workspace in Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:23.274320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84f9c205-b419-4d1f-8bbd-d69524c3b11d · outbound

This paper cites Coordination Among Neural Modules Through a Shared Global Workspace.

Verbalizable Representations Form a Global Workspace in Language Models Coordination Among Neural Modules Through a Shared Global Workspace

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:22.713495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20150452-521e-4724-9a2f-6b4ea71ca8b6 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:22.910007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f38ce1-663c-46e3-ac52-543e31dfeb94 · outbound

This paper cites Overthinking the Truth: Understanding how Language Models Process False Demonstrations.

Verbalizable Representations Form a Global Workspace in Language Models Overthinking the Truth: Understanding how Language Models Process False Demonstrations

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:23.697841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b3a680a-d518-4581-b715-9dc7a2303681 · outbound

This paper cites How does gpt-2 com- pute greater-than?: Interpreting mathematical abilities in a pre-trained language model.Advances in Neural Information Processing Systems, 36:76033–76060,.

Verbalizable Representations Form a Global Workspace in Language Models How does gpt-2 com- pute greater-than?: Interpreting mathematical abilities in a pre-trained language model.Advances in Neural Information Processing Systems, 36:76033–76060,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:23.846148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4282052-0b48-4cd2-a8c1-80dab0433a15 · outbound

This paper cites Universal Neurons in GPT2 Language Models.

Verbalizable Representations Form a Global Workspace in Language Models Universal Neurons in GPT2 Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:23.410991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfc7aa8d-a76d-4d40-a6f9-9135b24dac8c · outbound

This paper cites When models manipulate manifolds: The geometry of a counting task.

Verbalizable Representations Form a Global Workspace in Language Models When models manipulate manifolds: The geometry of a counting task

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:23.559598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1a5f40-88ae-4926-903e-7a8ed99d19a2 · outbound

This paper cites Linearity of Relation Decoding in Transformer Language Models.

Verbalizable Representations Form a Global Workspace in Language Models Linearity of Relation Decoding in Transformer Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.524953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 897f92ff-492c-46d9-9b2e-e06dcf1ada7f · outbound

This paper cites Designing and Interpreting Probes with Control Tasks.

Verbalizable Representations Form a Global Workspace in Language Models Designing and Interpreting Probes with Control Tasks

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.669373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1efd9d-d3b9-4f3b-b09b-7036439ed632 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.022604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06607832-d611-49df-921a-c2c74288dcde · outbound

This paper cites In-context learning creates task vectors.

Verbalizable Representations Form a Global Workspace in Language Models In-context learning creates task vectors

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.216440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b41883e7-602d-4bab-8372-7f93c931f0db · outbound

This paper cites Measuring massive multitask language understanding.International Con- ference on Learning Representations (ICLR), 2021.

Verbalizable Representations Form a Global Workspace in Language Models Measuring massive multitask language understanding.International Con- ference on Learning Representations (ICLR), 2021

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.348666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c25feb91-f3ac-46db-8c6f-dc5650e7c8d3 · outbound

This paper cites A process dissociation framework: Separating automatic from intentional uses of memory.Journal of memory and language, 30(5):513–541, 1991.

Verbalizable Representations Form a Global Workspace in Language Models A process dissociation framework: Separating automatic from intentional uses of memory.Journal of memory and language, 30(5):513–541, 1991

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:25.275365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e4bb17a-44ff-451d-b3eb-6a4a581902fc · outbound

This paper cites Characterizing stable regions in the residual stream of LLMs.

Verbalizable Representations Form a Global Workspace in Language Models Characterizing stable regions in the residual stream of LLMs

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:25.414008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25df6b00-1379-44d0-b7b7-1578c5fdf43c · outbound

This paper cites A structural probe for finding syntax in word representations.

Verbalizable Representations Form a Global Workspace in Language Models A structural probe for finding syntax in word representations

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.807605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91aeda39-4e57-4192-879d-a4631ccf4c74 · outbound

This paper cites Fast weight programming and linear transformers: from machine learning to neurobiology.arXiv preprint arXiv:2508.08435, 2025.

Verbalizable Representations Form a Global Workspace in Language Models Fast weight programming and linear transformers: from machine learning to neurobiology.arXiv preprint arXiv:2508.08435, 2025

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:24.930238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca9b602-cdbe-418c-836f-ae0d33631d54 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:25.175081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6263087a-9ae7-40b1-a40f-ebb63a10a8a4 · outbound

This paper cites Language Models (Mostly) Know What They Know.

Verbalizable Representations Form a Global Workspace in Language Models Language Models (Mostly) Know What They Know

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.160954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7ad0748-cb5f-4efd-b51a-0cb18fd7d52c · outbound

This paper cites macmillan, 2011.

Verbalizable Representations Form a Global Workspace in Language Models macmillan, 2011

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.300275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 415d25c3-eef2-4128-8835-0b3d4395b08b · outbound

This paper cites Lan- guage models are capable of metacognitive monitoring and control of their internal activa- tions.arXiv preprint arXiv:2505.13763, 2025.

Verbalizable Representations Form a Global Workspace in Language Models Lan- guage models are capable of metacognitive monitoring and control of their internal activa- tions.arXiv preprint arXiv:2505.13763, 2025

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:25.574344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc020cd-ce0f-4f89-b57d-38867223c64e · outbound

This paper cites Backward Lens: Projecting Language Model Gradients into the Vocabulary Space.

Verbalizable Representations Form a Global Workspace in Language Models Backward Lens: Projecting Language Model Gradients into the Vocabulary Space

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.836019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8b6a24-f2ca-453a-b294-e6c1cd764c2d · outbound

This paper cites Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens.

Verbalizable Representations Form a Global Workspace in Language Models Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:25.901469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c3607d2-1e76-4418-baa6-0fd33a89ea3f · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Verbalizable Representations Form a Global Workspace in Language Models TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.020144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de42415f-8cc4-467c-91b0-219ea467e1e0 · outbound

This paper cites Building transformers from neu- rons and astrocytes.Proceedings of the National Academy of Sciences, 120(34):e2219150120,.

Verbalizable Representations Form a Global Workspace in Language Models Building transformers from neu- rons and astrocytes.Proceedings of the National Academy of Sciences, 120(34):e2219150120,

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.315887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b12914-ff66-4388-b3c1-3292c675f2f1 · outbound

This paper cites AtP*: An efficient and scalable method for localizing LLM behaviour to components.

Verbalizable Representations Form a Global Workspace in Language Models AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.600435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c73023eb-0142-48bc-96c2-91a7d49ca84d · outbound

This paper cites Tracing attention computation through feature interactions.Transformer Circuits Thread,.

Verbalizable Representations Form a Global Workspace in Language Models Tracing attention computation through feature interactions.Transformer Circuits Thread,

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.403868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c7fc135-31ff-4e35-a7a6-162df9da1fbc · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.519224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d0f9017-b90f-4ff8-ab0c-5c9e0db91938 · outbound

This paper cites Activation oracles: Training and evaluating llms as general-purpose activation explainers.

Verbalizable Representations Form a Global Workspace in Language Models Activation oracles: Training and evaluating llms as general-purpose activation explainers

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.682523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fb2f18c-e0d7-445e-b6af-eb3128182f59 · outbound

This paper cites Me, myself, and ai: The situational awareness dataset (sad) for llms.Advances in Neural Information Processing Systems, 37:64010–64118, 2024.

Verbalizable Representations Form a Global Workspace in Language Models Me, myself, and ai: The situational awareness dataset (sad) for llms.Advances in Neural Information Processing Systems, 37:64010–64118, 2024

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:28.149086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e639387-1cea-4e88-8586-6f099fedb402 · outbound

This paper cites The cognitive unconscious.Science, 237(4821):1445–1452, 1987.

Verbalizable Representations Form a Global Workspace in Language Models The cognitive unconscious.Science, 237(4821):1445–1452, 1987

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:26.990268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65bd2ff-206e-47ee-b842-1ea572e9c0d5 · outbound

This paper cites Similarity of neural network representations revisited.

Verbalizable Representations Form a Global Workspace in Language Models Similarity of neural network representations revisited

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.161087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb6d503d-847b-41e5-8334-18794be5cf5c · outbound

This paper cites Empirical support for higher-order theories of conscious awareness.Trends in cognitive sciences, 15(8):365–373, 2011.

Verbalizable Representations Form a Global Workspace in Language Models Empirical support for higher-order theories of conscious awareness.Trends in cognitive sciences, 15(8):365–373, 2011

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:28.559068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35259f25-0d36-4b67-b547-b4973e6e7002 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.472713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ab6ea3-5c17-4441-b6d9-a11a7d710520 · outbound

This paper cites Self unbound: ego dissolution in psychedelic experience.

Verbalizable Representations Form a Global Workspace in Language Models Self unbound: ego dissolution in psychedelic experience

Reference 93

Resolution: verified exact; doi, observed 2026-08-01T23:19:03.024895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9d30bf15-a1d7-4f8b-8fcf-097617a8a979 · outbound

This paper cites LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs.

Verbalizable Representations Form a Global Workspace in Language Models LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.706801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a73ef8-150f-4674-9101-62cf2a04c5e4 · outbound

This paper cites Large Associative Memory Problem in Neurobiology and Machine Learning.

Verbalizable Representations Form a Global Workspace in Language Models Large Associative Memory Problem in Neurobiology and Machine Learning

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.830495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a530284-4b68-4d63-9363-2b54b34371ab · outbound

This paper cites The Remarkable Robustness of LLMs: Stages of Inference?.

Verbalizable Representations Form a Global Workspace in Language Models The Remarkable Robustness of LLMs: Stages of Inference?

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:27.971817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30e1a30d-cda0-46f7-a1b3-99273db5f393 · outbound

This paper cites Emergent introspective awareness in large language models.Trans- former Circuits Thread, 2025.

Verbalizable Representations Form a Global Workspace in Language Models Emergent introspective awareness in large language models.Trans- former Circuits Thread, 2025

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:29.072161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 618e5c04-cc65-412d-aa4a-c59af28deff0 · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 98

Resolution: verified exact; doi, observed 2026-08-01T23:19:03.451360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ed6dcf15-9fa0-494c-bf84-164872d023ab · outbound

This paper cites an unresolved cited work.

Verbalizable Representations Form a Global Workspace in Language Models Unresolved cited work

Reference 99

Resolution: verified exact; doi, observed 2026-08-01T23:19:03.190307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0727bd27-70cd-49f8-b6d6-017043cfb9d2 · outbound

This paper cites Introspective capabilities in large language models.Journal of Consciousness Studies, 30(9-10):143–153, 2023.

Verbalizable Representations Form a Global Workspace in Language Models Introspective capabilities in large language models.Journal of Consciousness Studies, 30(9-10):143–153, 2023

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:29.378313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322759d2-a828-403a-89b9-196fa3ae6ba1 · outbound

This paper cites Sparse Autoencoders Do Not Find Canonical Units of Analysis.

Verbalizable Representations Form a Global Workspace in Language Models Sparse Autoencoders Do Not Find Canonical Units of Analysis

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:28.686940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e6ca4a-ddca-4677-90ec-d02c09dda7af · outbound

This paper cites Paths not taken: Under- standing and mending the multilingual factual recall pipeline.

Verbalizable Representations Form a Global Workspace in Language Models Paths not taken: Under- standing and mending the multilingual factual recall pipeline

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:29.682340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0488b12-21b3-4476-adec-80f1cc357e08 · outbound

This paper cites Inference-Time Intervention: Eliciting Truthful Answers from a Language Model.

Verbalizable Representations Form a Global Workspace in Language Models Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:28.839363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7360eb3e-f76e-4c45-96d1-03cda6b3410f · outbound

This paper cites Understanding and Patching Compositional Reasoning in LLMs.

Verbalizable Representations Form a Global Workspace in Language Models Understanding and Patching Compositional Reasoning in LLMs

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:28.855826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4e116baa-ac9f-46d5-b69d-7668bedd4a8a · inbound

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model cites this paper.

Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model Verbalizable Representations Form a Global Workspace in Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T10:59:55.350406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae59fc80-2cd8-41a8-9f87-112fcf225a01 · inbound

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures cites this paper.

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures Verbalizable Representations Form a Global Workspace in Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T04:38:47.969437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72864568-5328-4f4f-8581-c2da0bc63895 · inbound

Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs cites this paper.

Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs Verbalizable Representations Form a Global Workspace in Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T00:41:18.194278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4580ec4-2531-4c3c-8e22-d37c94991838 · inbound

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility cites this paper.

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility Verbalizable Representations Form a Global Workspace in Language Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:33:56.173652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ce5e1525-4f6f-4903-bfd8-b2eeb4985744 · inbound

Interpreting Language Model Hidden States at Scale cites this paper.

Interpreting Language Model Hidden States at Scale Verbalizable Representations Form a Global Workspace in Language Models

Reference 116

Resolution: unresolved; no resolver link, observed 2026-08-14T04:16:17.156994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ae84ee-1e88-4d16-90ba-ec55364dff22 · inbound

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning cites this paper.

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning Verbalizable Representations Form a Global Workspace in Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:56.777542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.