INDEX
Explanations
references to black individuals involved in the slave trade
New Auto-Interp
Negative Logits
infallib
-0.59
SwiftUI
-0.56
view
-0.55
view
-0.55
othelioma
-0.54
EndInit
-0.54
Hecho
-0.53
Mutagenicity
-0.53
횟
-0.53
дент
-0.53
POSITIVE LOGITS
slave
0.98
slavery
0.96
slave
0.92
Slavery
0.86
Slave
0.82
escla
0.81
slaves
0.79
Slave
0.79
escra
0.78
schia
0.77
Activations Density 0.256%