INDEX
Explanations
The neuron activates on mentions of “putt” and related putting terms in a golf context (e.g. putt, putting, putter).
New Auto-Interp
Negative Logits
卫生
-0.06
jualan
-0.06
_UL
-0.06
milieu
-0.06
slapped
-0.06
следует
-0.06
upro
-0.06
(horizontal
-0.06
intertwined
-0.05
nah
-0.05
POSITIVE LOGITS
nett
0.07
Reviewer
0.07
_REMOVE
0.07
사항
0.07
consenting
0.07
Pieces
0.07
زي
0.07
ereum
0.06
ritt
0.06
ething
0.06
Activations Density 0.002%