INDEX
Explanations
references to historical figures and movements related to civil rights
New Auto-Interp
Negative Logits
Ŀ
-0.15
iyas
-0.15
emm
-0.14
IS
-0.14
433
-0.14
ulace
-0.14
depreciation
-0.14
esz
-0.14
irical
-0.14
avo
-0.14
POSITIVE LOGITS
ML
0.36
civil
0.29
Martin
0.28
ML
0.26
Civil
0.25
Martin
0.24
Birmingham
0.23
Montgomery
0.22
196
0.21
Rosa
0.21
Activations Density 0.113%