INDEX
Explanations
The neuron strongly activates on explicit sexual descriptions—particularly mentions of genital stimulation or arousal.
New Auto-Interp
Negative Logits
kes
-0.07
Pale
-0.06
Defaults
-0.06
screaming
-0.06
Moon
-0.06
bubble
-0.06
Bien
-0.06
SAS
-0.06
ują
-0.06
Cartesian
-0.06
POSITIVE LOGITS
ontvang
0.06
Playboy
0.06
름
0.06
rounding
0.06
пан
0.06
acknowledged
0.06
로서
0.06
块
0.06
&ZeroWidthSpace
0.06
_CHANNEL
0.05
Activations Density 0.040%