INDEX
Explanations
phrases related to movement and emotional transitions
New Auto-Interp
Negative Logits
imz
-0.15
šem
-0.14
ensi
-0.14
raisal
-0.14
backed
-0.13
ëĿ½
-0.13
coast
-0.13
ÑģÑĤанÑĥ
-0.13
eyer
-0.13
sink
-0.13
POSITIVE LOGITS
ROID
0.17
abbage
0.16
ãĤ§
0.15
ienes
0.14
subTitle
0.14
Herman
0.14
мÑĭ
0.14
Hang
0.14
Hanging
0.13
éĢł
0.13
Activations Density 0.608%