INDEX
Explanations
numerical values and percentages
New Auto-Interp
Negative Logits
unb
-0.17
chronic
-0.15
woo
-0.15
wer
-0.14
enery
-0.14
apk
-0.14
Abs
-0.14
ysz
-0.14
Abs
-0.14
sbin
-0.14
POSITIVE LOGITS
Įĵ
0.16
vil
0.15
indre
0.14
lesen
0.14
ÑĤен
0.14
ÑģÑĤад
0.14
gettext
0.14
eum
0.14
ssel
0.14
ascus
0.13
Activations Density 0.000%