4 stories tagged with #interpretability, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Interpretability"
RELATED TAGS
ARXIV.ORG
Refusal Lives Downstream of Persona in Chat Models
arXiv:2606.26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but…
ARXIV.ORG
How sure is the activation oracle?
Activation oracles aim to make the activations of other models legible to humans and yield promising results compared to white-box interpretability techniques. However, uncertainty…
OUTCRY AI
AI Interpretability Is a Revolutionary Skill
A language model has roughly sixty-five thousand internal concepts. None of them is the word your movement uses. Here is where the missing word actually lives — and how to put it t…
SEANGOEDECKE