INDEX
Explanations
references to civil rights and related legislative terms
New Auto-Interp
Negative Logits
ÃŃd
-0.16
A
-0.15
Sp
-0.14
ãĥ¼ãĥĨãĤ£
-0.14
ibar
-0.14
cer
-0.14
scalar
-0.14
kle
-0.14
ikit
-0.14
Scalar
-0.14
POSITIVE LOGITS
ANTE
0.21
Ant
0.18
ahn
0.17
ant
0.16
antu
0.16
anth
0.16
ag
0.15
Ant
0.15
Hust
0.15
antar
0.15
Activations Density 0.033%