INDEX
Explanations
terms related to Black individuals and communities
New Auto-Interp
Negative Logits
_hz
-0.16
itemid
-0.15
isure
-0.14
èģŀ
-0.14
bpp
-0.14
ysi
-0.13
okud
-0.13
Distributed
-0.13
ously
-0.13
obo
-0.13
POSITIVE LOGITS
quina
0.17
ve
0.15
tip
0.15
ened
0.15
unde
0.15
enen
0.15
selectAll
0.14
229
0.14
traits
0.14
leur
0.14
Activations Density 0.058%