INDEX
Explanations
criticisms or negative evaluations
expressions of negativity or dissatisfaction, particularly using the word "suck"
New Auto-Interp
Negative Logits
teness
-0.72
SPONSORED
-0.72
isations
-0.72
isation
-0.68
Nou
-0.68
uclear
-0.68
merce
-0.67
iami
-0.65
nsic
-0.63
gran
-0.62
POSITIVE LOGITS
suck
0.98
dick
0.95
bowl
0.90
sucked
0.88
eries
0.84
sucking
0.84
rider
0.82
glers
0.81
iddles
0.79
plug
0.79
Activations Density 0.004%