INDEX
Explanations
the name "Kay" followed by a number
mentions of the name "Kay."
New Auto-Interp
Negative Logits
urally
-0.80
atmosp
-0.75
pection
-0.72
grease
-0.71
ictions
-0.69
untled
-0.69
ionage
-0.68
naires
-0.68
nesota
-0.66
ioch
-0.66
POSITIVE LOGITS
leigh
1.11
la
1.06
Kay
1.00
von
0.91
Kay
0.88
tor
0.86
akers
0.84
den
0.83
ak
0.82
lee
0.82
Activations Density 0.009%