INDEX
Explanations
This neuron responds to mentions of substantial financial resources or wealth.
New Auto-Interp
Negative Logits
ени
-0.06
výsled
-0.06
암
-0.06
dispatch
-0.06
alous
-0.06
фун
-0.06
SPORT
-0.06
ância
-0.06
شنبه
-0.06
biases
-0.06
POSITIVE LOGITS
GE
0.06
Brook
0.06
.bat
0.06
ダイ
0.06
_SENT
0.06
)frame
0.06
ToProps
0.06
newcom
0.06
millions
0.06
subrange
0.06
Activations Density 0.025%