INDEX
Explanations
mentions of the name "Kevin"
mentions of the name "Kevin."
New Auto-Interp
Negative Logits
mented
-0.68
mitted
-0.67
atari
-0.66
regulated
-0.62
drive
-0.62
schild
-0.61
edded
-0.61
claimed
-0.59
suit
-0.59
opian
-0.58
POSITIVE LOGITS
Durant
0.95
Roose
0.95
Bacon
0.92
Rudd
0.91
Faul
0.86
Pillar
0.84
Piet
0.82
McH
0.82
ŃĶ
0.81
Garn
0.81
Activations Density 0.024%