INDEX
Explanations
names of political figures, particularly those associated with the Democratic Party
New Auto-Interp
Negative Logits
ilian
-0.15
ughs
-0.14
ollo
-0.14
uso
-0.14
ileaks
-0.14
umer
-0.14
ãĥ¼ãĥĢ
-0.14
ital
-0.14
agh
-0.14
strand
-0.14
POSITIVE LOGITS
anger
0.16
sky
0.15
sky
0.14
aya
0.14
RESERVED
0.14
Sky
0.14
Sky
0.14
chia
0.14
../../../../
0.14
comb
0.13
Activations Density 0.021%