3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Revised independent preprint, version 1.0.0. This preprint was revised in response to reviewer feedback from the NeurIPS 2026 workshop Interpretability as a Science (InterpScience). It is not an accepted workshop paper or a conference proceedings paper. We distinguish information readable from hidden states from its ca...
Exploratory preprint, version 0.1. We use dépaysement as a probe of whether activation steering can change the roles of familiar objects while preserving readable scene continuity. A selector-free study crosses two prompts and three steering strengths over 12 mundane scenes. Medium steering increases an observer-labele...
Exploratory preprint, version 0.1. We use dépaysement as a probe of whether activation steering can change the roles of familiar objects while preserving readable scene continuity. A selector-free study crosses two prompts and three steering strengths over 12 mundane scenes. Medium steering increases an observer-labele...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
