INDEX
Explanations
references to vice presidential candidates, particularly focusing on Kamala Harris
New Auto-Interp
Negative Logits
ampa
-0.18
_ASCII
-0.15
å©Ĩ
-0.15
incinn
-0.15
оÑı
-0.15
Hra
-0.15
Ľå»º
-0.14
çŃĴ
-0.14
æŃ
-0.14
apan
-0.14
POSITIVE LOGITS
jug
0.16
eu
0.15
κÏĮ
0.14
ck
0.14
/world
0.14
mb
0.14
éĻ
0.14
caliber
0.14
tok
0.13
iz
0.13
Activations Density 0.015%