INDEX
Explanations
occurrences of the term "Nam" and its variants
New Auto-Interp
Negative Logits
inosaur
-0.15
eger
-0.15
uer
-0.14
erner
-0.14
psz
-0.14
addtogroup
-0.14
aux
-0.14
aidu
-0.13
pch
-0.13
aan
-0.13
POSITIVE LOGITS
ibia
0.31
aste
0.27
ASTE
0.21
ÄĽstÃŃ
0.21
astes
0.19
orado
0.17
deo
0.16
sod
0.16
ysl
0.16
æı
0.16
Activations Density 0.007%