INDEX
Explanations
statistics and numerical data related to demographics and educational achievements
New Auto-Interp
Negative Logits
vez
-0.18
nal
-0.15
Bord
-0.15
iming
-0.15
aval
-0.15
istrovstvÃŃ
-0.14
_UNDEF
-0.14
/TT
-0.14
oksen
-0.14
arda
-0.13
POSITIVE LOGITS
عات
0.15
xes
0.14
주
0.14
agara
0.14
igits
0.14
wen
0.14
lobe
0.14
ī´
0.14
unr
0.14
Luo
0.14
Activations Density 0.273%