INDEX
Explanations
the name "Kevin" in various contexts
New Auto-Interp
Negative Logits
yrinth
-0.82
schild
-0.79
bler
-0.68
rants
-0.67
mented
-0.67
MENTS
-0.65
cffffcc
-0.64
regulated
-0.64
mitted
-0.64
payment
-0.63
POSITIVE LOGITS
Rudd
0.95
Durant
0.90
Bacon
0.88
arios
0.87
Faul
0.83
McH
0.82
ize
0.81
Kis
0.80
ists
0.80
istic
0.79
Activations Density 0.015%