INDEX
Explanations
words related to liquor
references to alcoholic beverages and liquor-related topics
New Auto-Interp
Negative Logits
Canterbury
-0.68
Hawk
-0.65
Aj
-0.65
DIR
-0.64
wered
-0.63
pta
-0.63
Shogun
-0.62
atari
-0.61
verty
-0.59
Steps
-0.58
POSITIVE LOGITS
liquor
1.08
cohol
1.07
Liqu
0.90
ocaust
0.88
istry
0.84
opoly
0.84
licence
0.83
beverage
0.83
igon
0.83
icultural
0.80
Activations Density 0.012%