INDEX
Explanations
phrases related to political hypocrisy and discrimination
New Auto-Interp
Negative Logits
eker
-0.15
ë´ī
-0.15
Kurum
-0.15
eyim
-0.14
kám
-0.14
ảng
-0.14
ucket
-0.13
ombat
-0.13
odzi
-0.13
calculator
-0.13
POSITIVE LOGITS
è²
0.17
when
0.16
ź
0.15
when
0.15
ewe
0.15
elephant
0.14
ULA
0.14
critical
0.14
Spi
0.14
ita
0.14
Activations Density 0.154%