INDEX
Explanations
This neuron activates on mentions of physical punishment implements (e.g., canes, paddles, clamps).
New Auto-Interp
Negative Logits
izr
-0.07
microscope
-0.07
_STORE
-0.06
Complex
-0.06
bán
-0.06
adero
-0.06
gles
-0.06
pioneered
-0.06
World
-0.06
spec
-0.06
POSITIVE LOGITS
záznam
0.06
cstdlib
0.06
kj
0.06
іли
0.06
rieben
0.06
(channel
0.06
ppers
0.06
accompagn
0.06
Nicole
0.06
esting
0.06
Activations Density 0.009%