INDEX
Explanations
demographic information such as age, race/ethnicity, sex, and gender
terms related to demographic factors
New Auto-Interp
Negative Logits
inka
-0.87
mud
-0.80
olin
-0.78
cour
-0.75
olars
-0.75
geons
-0.70
uba
-0.69
kus
-0.69
isse
-0.69
ebted
-0.68
POSITIVE LOGITS
affiliation
0.97
preference
0.88
preferences
0.81
affili
0.76
(%)
0.75
differences
0.72
Aff
0.72
nationality
0.72
suscept
0.71
(%
0.71
Activations Density 0.268%