INDEX
Explanations
names and titles related to African American studies and cultural representations
New Auto-Interp
Negative Logits
iasi
-0.15
unate
-0.14
ificates
-0.14
404
-0.14
numar
-0.14
etur
-0.13
Seal
-0.13
kyt
-0.13
achs
-0.13
-profit
-0.13
POSITIVE LOGITS
gre
0.22
bre
0.21
BRE
0.21
vre
0.21
URE
0.20
Bre
0.20
Bre
0.19
gre
0.19
Bret
0.18
Gre
0.18
Activations Density 0.048%