pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Finding Interpretable Prompt-Specific Circuits in Language Models

cs.LG · 2026-02-13 · unverdicted · novelty 6.0

ACC++ traces prompt-specific circuits in language models from one forward pass by extracting interpretable low-dimensional causal signals, revealing clustered mechanisms for indirect object identification and language-specific signals in multilingual settings.

citing papers explorer

Showing 1 of 1 citing paper.

  • Finding Interpretable Prompt-Specific Circuits in Language Models cs.LG · 2026-02-13 · unverdicted · none · ref 7

    ACC++ traces prompt-specific circuits in language models from one forward pass by extracting interpretable low-dimensional causal signals, revealing clustered mechanisms for indirect object identification and language-specific signals in multilingual settings.