pstore

Refusal in Language Models Is Mediated by a Single Direction

tags
link
https://proceedings.neurips.cc/paper_files/paper/2024/hash/f545448535dfde4f9786555403ab7c49-Abstract-Conference.html
zotero
zotero://select/library/items/ZMBCXP7Q
itemType
journalArticle
authors
pubDate
2024-12-16
retDate
2025-10-30
relatedProjects
DIY AI

Graph View

Backlinks