← back to paper

Review history

arxiv: 2604.25866 · 2 revisions

Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders

1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 6.0
   35411 ms 5724 in 1096 out 2026-07-01T08:40:37.196642+00:00
2. 2026-05-07 UNVERDICTED LOW v0.9.0 novelty 6.0
   76931 ms 5503 in 1437 out 2026-05-07T16:25:18.857279+00:00