INDEX
Explanations
mentions of the name "Kate" or variations of it
New Auto-Interp
Negative Logits
mature
-0.16
quets
-0.15
thern
-0.15
ansk
-0.14
rado
-0.14
å§
-0.14
tif
-0.14
Ø©
-0.14
weigh
-0.14
IFT
-0.14
POSITIVE LOGITS
ÅĻ
0.25
y
0.22
Middleton
0.18
Moss
0.16
Mara
0.15
Wins
0.15
middle
0.15
éϵ
0.15
lege
0.15
hz
0.15
Activations Density 0.005%