INDEX
Explanations
names or words related to gambling
words or phrases related to gambling or games
New Auto-Interp
Negative Logits
alli
-0.74
erva
-0.70
ancial
-0.69
ellar
-0.69
Ernst
-0.68
ohn
-0.67
ournal
-0.67
ortium
-0.67
orters
-0.66
799
-0.65
POSITIVE LOGITS
bles
1.10
ble
1.05
bling
0.82
bly
0.82
theless
0.81
bled
0.80
vous
0.80
grass
0.77
tt
0.77
Doodle
0.77
Activations Density 0.009%