INDEX
Explanations
mentions of racial issues and attitudes
New Auto-Interp
Negative Logits
ä»Ļ
-0.14
NSS
-0.14
ARGIN
-0.14
çͲ
-0.14
auss
-0.14
cky
-0.14
Seks
-0.14
croll
-0.13
ecal
-0.13
ftype
-0.13
POSITIVE LOGITS
African
0.58
black
0.50
race
0.48
Black
0.48
blacks
0.46
Afro
0.44
frican
0.43
african
0.43
Black
0.43
black
0.43
Activations Density 0.731%