INDEX
Explanations
words related to cults and fan followings
occurrences of the word "cult" and related phrases
New Auto-Interp
Negative Logits
forth
-0.68
deen
-0.67
Lag
-0.61
berry
-0.61
cknowled
-0.61
Pik
-0.60
Downloadha
-0.59
Ness
-0.59
Stra
-0.59
Kay
-0.57
POSITIVE LOGITS
ivating
1.19
ivated
1.14
ivation
1.12
urally
1.05
ists
1.04
ogenic
0.98
urable
0.94
ura
0.92
ishly
0.91
ures
0.88
Activations Density 0.037%