Sentiment
Users praise the AITC 2026 Conference for efforts making interpretability techniques accessible to other-domain experts via the poster session.
Pos
100.0%
Neg
0.0%
1 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS584BOOKMARKS2
Yonatan Belinkov@boknilev
Octavian Machidon comparing moral judgements in humans and LLMs
Yonatan Belinkov@boknilev
@carstenlanquillon
20hViews 584Likes 1Bookmarks 2
LIKES2REPLIES1
Yonatan Belinkov@boknilev
@lanqui on refusal formation areas in different layers and the gap between recognizing harm and refusing
Yonatan Belinkov@boknilev
Octavian Machidon comparing moral judgements in humans and LLMs
20hViews 557Likes 2Bookmarks 1
Yonatan Belinkov@boknilev
@lanqui In the poster session, nice effort for making Interpretability techniques accessible to experts from other domains
Yonatan Belinkov@boknilev
@lanqui on refusal formation areas in different layers and the gap between recognizing harm and refusing
20hViews 82Likes 0Bookmarks 0