INDEX
Explanations
mentions of the name "Ken"
mentions of the name "Ken."
New Auto-Interp
Negative Logits
xual
-0.83
confir
-0.80
pmwiki
-0.78
anwhile
-0.76
exha
-0.75
Reloaded
-0.74
Ö¼
-0.67
sensitive
-0.66
plural
-0.66
conclud
-0.64
POSITIVE LOGITS
zie
1.01
yon
0.99
ji
0.97
ois
0.95
wei
0.91
ichi
0.89
zen
0.88
zo
0.88
leys
0.82
obi
0.81
Activations Density 0.010%