INDEX
Explanations
mentions of African-American communities, racial disparities, and social injustice related to African-Americans
New Auto-Interp
Negative Logits
Shutterstock
-0.73
pload
-0.71
Pastebin
-0.63
Dickinson
-0.63
constitu
-0.63
shutter
-0.61
earch
-0.59
lapt
-0.59
daq
-0.59
Gutenberg
-0.58
POSITIVE LOGITS
American
1.01
Americans
0.98
inspired
0.90
themed
0.88
origin
0.86
based
0.85
sounding
0.84
style
0.83
derived
0.82
induced
0.80
Activations Density 8.126%