INDEX
Explanations
past tense verbs
This neuron activates on language describing characters removing clothes or being undressed (exposure readiness).
New Auto-Interp
Negative Logits
ovu
-0.07
']),↵
-0.07
Jane
-0.06
Kevin
-0.06
ouples
-0.06
primarily
-0.06
except
-0.06
Lena
-0.06
Mercy
-0.06
cumulative
-0.06
POSITIVE LOGITS
("."0.07
_modal
0.07
GObject
0.07
!important
0.07
mess
0.06
plen
0.06
AGMA
0.06
.b
0.06
UMAN
0.06
ss
0.06
Activations Density 0.029%