INDEX
Explanations
references to Native American identity and historical events
New Auto-Interp
Negative Logits
rural
-0.14
qing
-0.14
Rural
-0.14
ynos
-0.13
jelly
-0.13
abd
-0.13
bombed
-0.13
rex
-0.13
cid
-0.13
梨
-0.13
POSITIVE LOGITS
Chief
0.32
Indians
0.32
Indian
0.32
chiefs
0.31
Native
0.30
Chief
0.30
Chiefs
0.29
chief
0.28
Pow
0.27
Medicine
0.27
Activations Density 0.057%