INDEX
Explanations
references to the holiday season and related festivities
New Auto-Interp
Negative Logits
ayar
-0.18
oster
-0.16
wij
-0.15
anvas
-0.15
si
-0.15
etten
-0.14
ode
-0.14
ka
-0.14
oda
-0.14
Kültür
-0.14
POSITIVE LOGITS
season
0.17
Periph
0.16
-season
0.16
ÑĢÑĮ
0.15
December
0.14
lica
0.14
haul
0.14
ALS
0.14
uso
0.14
DITION
0.14
Activations Density 0.033%