INDEX
Explanations
mentions of the name "Tom."
New Auto-Interp
Negative Logits
ãģĴ
-0.19
udos
-0.16
utz
-0.15
quier
-0.15
ienne
-0.15
uset
-0.15
aub
-0.14
ãĥĭãĤ¢
-0.14
neau
-0.14
uckle
-0.14
POSITIVE LOGITS
pid
0.18
Fel
0.16
islav
0.16
Siz
0.15
fel
0.15
าย
0.15
BS
0.15
Cruise
0.14
oken
0.14
ford
0.14
Activations Density 0.009%