INDEX
Explanations
mentions of development projects and associated teams
New Auto-Interp
Negative Logits
/Dk
-0.15
Erotische
-0.14
Prostitutas
-0.13
Ïģει
-0.13
alıdır
-0.13
ÑĢоÑĪ
-0.13
à¸łà¸²à¸©
-0.13
gnore
-0.13
повÑĸд
-0.13
ÙĴس
-0.13
POSITIVE LOGITS
Named
0.31
Selected
0.29
Earn
0.29
Rece
0.29
named
0.28
Wins
0.28
selected
0.26
chosen
0.26
Jo
0.26
Recogn
0.25
Activations Density 0.147%