INDEX
Explanations
expressions of strong emotions and sentiments
New Auto-Interp
Negative Logits
atables
-0.16
anja
-0.15
cors
-0.15
#End
-0.15
orio
-0.14
untime
-0.14
odo
-0.14
Äįet
-0.14
unos
-0.14
aland
-0.14
POSITIVE LOGITS
беÑĢ
0.14
/go
0.14
iest
0.13
rip
0.13
Åĵ
0.13
entitled
0.13
swick
0.13
rip
0.13
Âľ
0.13
rap
0.13
Activations Density 0.063%