INDEX
Explanations
mentions of different types of alcoholic beverages, particularly bourbon and whiskey
references to various types of alcoholic beverages, particularly bourbon and whiskey
New Auto-Interp
Negative Logits
uders
-0.77
ularity
-0.76
lez
-0.74
fter
-0.73
ULAR
-0.73
swer
-0.70
nda
-0.69
ospace
-0.68
rator
-0.66
srf
-0.66
POSITIVE LOGITS
whiskey
1.36
whisky
1.31
Whis
1.14
bourbon
0.99
Scotch
0.96
tasting
0.91
whis
0.90
vodka
0.90
Bourbon
0.87
distilled
0.87
Activations Density 0.019%