~/bad-microscopeThe tool is wrong, not the neuron. Feature visualization reward-hacked into dog basins in InceptionV1's late layers; SwiGLU's double-negative regime puts a sign-flipped echo at the top of a neuron's activation list; short contexts hide long-context neurons.
~/recursive-generalizationA neuron generalizes along one axis, then sprouts offshoots from those: iy, diy, do it yourself. Grouped things are near each other in some semantic space, and the branching is visible over training checkpoints.
no votes on this pair in this scope yet
you’ll log in, then return to this pair to cast your vote.