INDEX
Explanations
names of a person named Nicole
mentions of the name "Nicole."
New Auto-Interp
Negative Logits
poke
-0.72
ansas
-0.70
quartered
-0.70
olver
-0.67
igmatic
-0.67
akedown
-0.66
root
-0.66
blaster
-0.65
oster
-0.65
EEK
-0.65
POSITIVE LOGITS
tto
0.94
tes
0.90
tta
0.88
ga
0.87
tti
0.86
lette
0.80
gur
0.79
Scher
0.79
tesy
0.79
Kid
0.78
Activations Density 0.020%