thebes(@voooooogel):worth noting with the recent "persona neurons" trend: just because a steering intervention induces a persona change, doesn't mean the vector or neuron being steered is persona-specific. models seem to do something like "persona solving" under steering https://t.co/C5QXiGncEs

thebes

@voooooogel

ꙮ in a moment, in the twinkling of an eye, ꙮ blog/art/fiction ꙮ llm psych @acsresearchorg ꙮ 💞💍📝 @holotopian

加入 April 2011

1.2K 正在關注 22.8K 粉絲

thebes@voooooogel

2026.10.29 06:03

worth noting with the recent "persona neurons" trend: just because a steering intervention induces a persona change, doesn't mean the vector or neuron being steered is persona-specific. models seem to do something like "persona solving" under steering