INDEX
Explanations
mentions of personal names, specifically the name "Keith"
mentions of the name "Keith."
New Auto-Interp
Negative Logits
xual
-0.74
unres
-0.63
TOR
-0.61
aged
-0.60
prevail
-0.60
housing
-0.60
اÙĦ
-0.59
CHO
-0.59
traff
-0.59
ienne
-0.57
POSITIVE LOGITS
Ellison
0.95
Jarrett
0.81
rett
0.80
Richards
0.77
Bedford
0.76
rey
0.75
osta
0.75
Humph
0.75
sonian
0.74
ulhu
0.72
Activations Density 0.040%