INDEX
Explanations
mentions of the name "Leonard."
New Auto-Interp
Negative Logits
Fé
-0.16
obra
-0.15
Barber
-0.15
arLayout
-0.15
lette
-0.14
itel
-0.14
ibi
-0.14
ToFront
-0.14
ÅĤÄħ
-0.14
itet
-0.14
POSITIVE LOGITS
Platt
0.15
ossier
0.15
ch
0.15
nP
0.14
LAG
0.14
ymph
0.14
cheng
0.14
state
0.14
chy
0.14
chip
0.14
Activations Density 0.004%