INDEX
Explanations
names of doctors or individuals related to the medical field
names of individuals, particularly those with the title "Dr."
New Auto-Interp
Negative Logits
ittees
-0.86
ģ«
-0.80
thumbnails
-0.76
thieves
-0.75
voters
-0.70
Thieves
-0.69
=]
-0.68
etimes
-0.67
fences
-0.66
thief
-0.65
POSITIVE LOGITS
Canaver
1.18
McCoy
0.88
âĸĪâĸĪâĸĪâĸĪ
0.82
Hubbard
0.81
etus
0.78
âĸĪ
0.77
Carson
0.77
keley
0.77
aimon
0.74
Freud
0.74
Activations Density 0.124%