INDEX
Explanations
references to eugenics and genetic concepts in historical contexts
New Auto-Interp
Negative Logits
omore
-0.16
NSSet
-0.16
iska
-0.15
CCA
-0.15
_DM
-0.15
ippi
-0.15
sple
-0.15
_IT
-0.15
ita
-0.15
ÑĤаб
-0.14
POSITIVE LOGITS
Bass
0.17
ANCH
0.17
AWN
0.16
anch
0.16
ODB
0.15
ual
0.15
bass
0.15
egral
0.15
cimal
0.15
chall
0.14
Activations Density 0.028%