Super interesting results. Do you have a sense of how much this is “the LLM targets the specific addressee” versus “the addressee’s name latently triggers related thoughts”?
As in, how much is it the LLM tailoring its response to Amanda Askell versus the name just triggering the LLM’s “oh yeah, LLMs are unaligned” factual circuits.
Super interesting results. Do you have a sense of how much this is “the LLM targets the specific addressee” versus “the addressee’s name latently triggers related thoughts”?
As in, how much is it the LLM tailoring its response to Amanda Askell versus the name just triggering the LLM’s “oh yeah, LLMs are unaligned” factual circuits.