ML Anthology
Authors
Search
About
Obeso, Oscar
1 publications
NeurIPS
2024
Refusal in Language Models Is Mediated by a Single Direction
Andy Arditi
,
Oscar Obeso
,
Aaquib Syed
,
Daniel Paleka
,
Nina Panickssery
,
Wes Gurnee
,
Neel Nanda