INDEX
Explanations
mentions of the name "Jack."
New Auto-Interp
Negative Logits
ImageContext
-0.65
:✨
-0.64
̈́
-0.63
للمعارف
-0.62
principalColumn
-0.58
Administrativna
-0.56
ticle
-0.56
queſta
-0.56
Bearbeiten
-0.55
Искәрмәләр
-0.55
POSITIVE LOGITS
cheer
0.60
whip
0.60
boosters
0.56
Induction
0.55
Whip
0.55
cheering
0.54
Boots
0.53
Induction
0.51
boots
0.51
Boo
0.51
Activations Density 0.220%