INDEX
Explanations
counts of people and groups in various contexts
New Auto-Interp
Negative Logits
_eof
-0.17
cken
-0.16
oproject
-0.16
afil
-0.14
ovie
-0.14
omu
-0.14
platz
-0.14
weather
-0.14
ichick
-0.14
ormal
-0.14
POSITIVE LOGITS
among
0.20
whose
0.19
amongst
0.17
who
0.16
Among
0.15
ÙĩÙĨ
0.15
among
0.15
571
0.14
Balt
0.14
those
0.14
Activations Density 0.217%