INDEX
Explanations
academic titles and leadership positions within organizations
New Auto-Interp
Negative Logits
deen
-0.17
nea
-0.15
Borders
-0.15
à¤Ĥधन
-0.15
him
-0.15
stal
-0.14
ÑĤо
-0.14
orian
-0.14
war
-0.14
lal
-0.14
POSITIVE LOGITS
Riv
0.16
.ColumnHeader
0.15
ercul
0.14
ÙĬرة
0.14
emple
0.14
gies
0.14
gie
0.14
verts
0.13
isbury
0.13
arget
0.13
Activations Density 0.047%