INDEX
Explanations
The neuron responds to explicit erotic sexual content—especially vivid references to genitalia and sexual acts.
New Auto-Interp
Negative Logits
ınızda
-0.06
spanking
-0.06
450
-0.06
́c
-0.06
marca
-0.06
systém
-0.06
-offs
-0.06
мало
-0.06
astos
-0.06
chaired
-0.06
POSITIVE LOGITS
推
0.06
hood
0.06
_SCRIPT
0.06
lical
0.06
drawn
0.06
_through
0.06
_based
0.06
귀
0.06
Global
0.06
.uint
0.06
Activations Density 0.014%