INDEX
Explanations
expressions of emotional connections and personal relationships
New Auto-Interp
Negative Logits
utas
-0.16
pivot
-0.14
whip
-0.14
ÑĨем
-0.14
ilon
-0.14
ÑĮми
-0.13
lobs
-0.13
etter
-0.13
ueva
-0.13
enta
-0.13
POSITIVE LOGITS
showing
0.47
show
0.44
showed
0.43
shows
0.42
Showing
0.40
SHOW
0.38
show
0.38
Showing
0.37
-show
0.33
Show
0.33
Activations Density 0.133%