INDEX
Explanations
This neuron detects mentions of modeling and fashion industry terms.
New Auto-Interp
Negative Logits
nummer
-0.06
ibilidad
-0.06
BP
-0.06
aber
-0.06
thickness
-0.06
amber
-0.06
ntax
-0.06
jandro
-0.06
eacher
-0.06
skému
-0.06
POSITIVE LOGITS
institutional
0.07
муж
0.07
Advertising
0.07
Platt
0.07
Model
0.07
UserModel
0.07
ordinary
0.06
Models
0.06
dětí
0.06
gcc
0.06
Activations Density 0.012%