INDEX
Explanations
references to admission fees or costs associated with events or locations
New Auto-Interp
Negative Logits
apos
-0.16
inka
-0.15
itaire
-0.14
ento
-0.14
iov
-0.13
é¬
-0.13
ajÄħc
-0.13
äs
-0.13
464
-0.13
fin
-0.13
POSITIVE LOGITS
ager
0.17
Specifier
0.15
bal
0.15
cock
0.15
lood
0.15
киÑģ
0.15
aging
0.14
ritz
0.14
olves
0.14
iece
0.14
Activations Density 0.064%