INDEX
Explanations
numerical references to dates and times
New Auto-Interp
Negative Logits
rám
-0.17
uien
-0.17
ábado
-0.14
issan
-0.14
avicon
-0.14
ichni
-0.14
omial
-0.14
igest
-0.14
stad
-0.14
TION
-0.14
POSITIVE LOGITS
sm
0.17
ipar
0.15
hi
0.15
515
0.15
str
0.15
cheer
0.15
Sm
0.15
Far
0.14
after
0.14
owie
0.14
Activations Density 0.046%