INDEX
Explanations
names of prominent individuals, specifically those in the entertainment industry
New Auto-Interp
Negative Logits
pac
-0.17
trad
-0.15
渡
-0.15
_pointer
-0.14
GINE
-0.14
ahlen
-0.14
.BorderFactory
-0.14
/provider
-0.14
ennie
-0.14
GC
-0.14
POSITIVE LOGITS
Robert
0.21
robert
0.19
Robert
0.19
Bob
0.19
Bob
0.19
veis
0.16
Bobby
0.15
bob
0.15
averse
0.14
athe
0.14
Activations Density 0.023%