INDEX
Explanations
body parts and movements in emotional contexts
New Auto-Interp
Negative Logits
ente
-0.18
ambah
-0.15
subst
-0.14
ÃĹ</
-0.14
ainer
-0.14
atak
-0.14
rips
-0.14
PRETTY
-0.14
OTA
-0.14
ivet
-0.14
POSITIVE LOGITS
виж
0.17
ickers
0.17
éĢļ
0.15
******************************************************************************↵
0.15
inda
0.14
aran
0.14
lifetime
0.14
@testable
0.14
figur
0.14
icker
0.14
Activations Density 0.200%