INDEX
Explanations
references to gold, mining, and associated activities
New Auto-Interp
Negative Logits
/forum
-0.17
eum
-0.16
oton
-0.16
ulen
-0.16
elter
-0.15
CAPE
-0.15
rupa
-0.14
ÄĽt
-0.14
ahun
-0.14
azi
-0.14
POSITIVE LOGITS
Wort
0.17
pert
0.16
Nap
0.15
eline
0.15
istes
0.15
ListViewItem
0.14
Duy
0.14
ằ
0.14
gra
0.14
ucs
0.14
Activations Density 0.055%