INDEX
Explanations
phrases with a rhetorical or sarcastic tone
expressions of skepticism or questioning statements
New Auto-Interp
Negative Logits
catentry
-0.90
ODUCT
-0.77
earchers
-0.72
ItemImage
-0.71
Initially
-0.71
Initial
-0.71
AFTA
-0.70
ITION
-0.69
displayText
-0.68
cffffcc
-0.68
POSITIVE LOGITS
goddamn
1.15
idiots
1.04
fucking
1.04
dudes
1.03
godd
1.03
ya
1.00
shit
0.99
dick
0.96
pissed
0.96
ain
0.95
Activations Density 1.762%