INDEX
Explanations
terms related to vineyards and winemaking
New Auto-Interp
Negative Logits
uler
-0.15
ç£
-0.15
лаг
-0.15
acts
-0.14
urred
-0.14
licher
-0.14
atives
-0.14
apter
-0.14
entina
-0.14
iaux
-0.13
POSITIVE LOGITS
SOURCE
0.16
yard
0.15
amel
0.14
ruh
0.14
idity
0.14
uz
0.14
bak
0.14
lis
0.14
Source
0.14
-source
0.14
Activations Density 0.009%