INDEX
Explanations
references to the term "craze" or "craving"
instances of the word "craze" and related cravings or desires
New Auto-Interp
Negative Logits
GOODMAN
-0.84
Democr
-0.79
manship
-0.74
acity
-0.72
gdala
-0.72
nikov
-0.71
DPRK
-0.70
rity
-0.67
iaries
-0.66
Shades
-0.66
POSITIVE LOGITS
igslist
1.48
fters
1.15
pload
1.05
ving
1.02
fter
1.01
ven
0.97
pton
0.92
isma
0.92
ves
0.89
issy
0.89
Activations Density 0.010%