Back to article
arxiv.org

Refusal in Language Models Is Mediated by a Single Direction (opens in new tab)

Covered by 4 sources See all sources covering this story including codeberg.org, lesswrong.comDiscussed on Hacker News

Feeds

✨ Discovered from this domain
[2406.11717] Refusal in Language Models Is Mediated by a Single Direction arxiv.org

Abstract page for arXiv paper 2406.11717: Refusal in Language Models Is Mediated by a Single Direction

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help