INDEX
Explanations
references to the name "Amy."
New Auto-Interp
Negative Logits
anos
-0.17
ç³»
-0.16
anje
-0.15
çīĮ
-0.15
chte
-0.15
icine
-0.15
tridge
-0.15
uder
-0.15
ispers
-0.14
.defaults
-0.14
POSITIVE LOGITS
gd
0.28
loid
0.27
Wine
0.21
Schumer
0.21
thest
0.20
GD
0.17
lose
0.17
ris
0.17
riad
0.16
ot
0.15
Activations Density 0.004%