INDEX
Explanations
phrases related to liquor
references to alcoholic beverages and liquor
New Auto-Interp
Negative Logits
pta
-0.73
Hawk
-0.69
knit
-0.67
Canterbury
-0.65
wered
-0.65
Aj
-0.64
DIR
-0.60
Ake
-0.60
humans
-0.59
Position
-0.59
POSITIVE LOGITS
liquor
1.00
ocaust
0.99
cohol
0.92
opoly
0.87
ice
0.86
beverage
0.83
istry
0.83
liqu
0.83
licence
0.80
Mechdragon
0.79
Activations Density 0.015%