INDEX
Explanations
the word "also" indicating additional information or context
New Auto-Interp
Negative Logits
tic
-0.73
c
-0.70
len
-0.70
Khat
-0.70
Marlon
-0.68
nik
-0.67
rio
-0.67
ly
-0.67
nin
-0.66
ni
-0.66
POSITIVE LOGITS
кож
1.11
ALSO
1.08
ALSO
1.06
Normdatei
1.04
Também
0.99
jsdelivr
0.99
וגם
0.97
wnież
0.97
turut
0.97
gså
0.97
Activations Density 0.139%