INDEX
Explanations
The neuron activates on mentions of bulimia nervosa and related binge-eating/purging disorder terms.
New Auto-Interp
Negative Logits
Jana
-0.07
ایالات
-0.06
หร
-0.06
mechanically
-0.06
Letters
-0.06
Permission
-0.06
기도
-0.06
overthrow
-0.06
trapping
-0.06
Angle
-0.06
POSITIVE LOGITS
烟
0.07
Bütün
0.07
.pg
0.07
_MEDIUM
0.06
adresse
0.06
Stalin
0.06
欧美
0.06
IU
0.06
قرار
0.06
EqualTo
0.06
Activations Density 0.001%