News for hackers. Stuff that matters.

A comment on TopoNets: High performing vision and language models with brain-like topography. Parent comment

Re:TopoNets: High performing vision and language models with... by mayukhdeb on Thursday January 30, 2025 @11:43PM (#42884760)
We localized "toxic" neurons by contrasting the activations of each neuron for toxic v/s normal texts. It's a method inspired by old-school neuroscience.
[ Parent | on HN ]
Re:TopoNets: High performing vision and language models with... by immibis on Friday January 31, 2025 @04:41AM (#42886150)
Defining all politics as toxic is concerning, if it's not just a proof of concept. That's something dictatorships do so that people won't speak up.
[ Parent | on HN ]