INDEX
Explanations
references to different types of wines
mentions of wine
New Auto-Interp
Negative Logits
aneous
-0.81
aneously
-0.79
ulation
-0.72
ordinate
-0.72
ulu
-0.70
urat
-0.70
uled
-0.70
DonaldTrump
-0.69
urtle
-0.68
WATCHED
-0.68
POSITIVE LOGITS
wine
1.16
tasting
1.12
wine
1.09
vinegar
1.08
grapes
1.05
cellar
1.00
tast
0.96
wines
0.93
vine
0.92
Wine
0.88
Activations Density 0.011%