Stargazer
s
.cn
观星势 知兴替
Menu
首页 Home
星势 Trending
对比 Compare
关于 About
首页
/
andyrdt
andyrdt
Github
Followers
NaNM
代码库
andyrdt/refusal_direction
391
Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
Python