INDEX
Explanations
references to the name "Gamble" or variations of it
words related to gambling
New Auto-Interp
Negative Logits
ellar
-0.77
ahime
-0.73
alli
-0.72
okin
-0.69
erva
-0.68
OLOG
-0.67
ohn
-0.66
Ernst
-0.65
ERA
-0.65
VERTISEMENT
-0.65
POSITIVE LOGITS
bles
1.24
ble
1.07
theless
0.99
vous
0.89
tt
0.89
bling
0.88
bled
0.86
bly
0.86
grass
0.85
bum
0.84
Activations Density 0.020%