LINKED LIST
[txt mode]
▸
Refusal in Language Models Is Mediate...
home
explore
|
log in
Refusal in Language Models Is Mediated by a Single Direction
arxiv.org · 2026-10-01 · 0 upvotes
log in
to save, upvote or flag this.
─── In 0 lists ─────────────────────────────────────────
(not in any lists yet)
related read on:
*
Pirate Face - The permanence layer for sovereign AI
(from the discussion)