INDEX
Explanations
mentions of a specific political figure, focusing on Kamala Harris
New Auto-Interp
Negative Logits
quarter
-0.15
رÙĪØ³
-0.14
cka
-0.14
printing
-0.14
ì¦Ŀ
-0.14
bart
-0.13
ìľ
-0.13
loa
-0.13
ainment
-0.13
ozilla
-0.13
POSITIVE LOGITS
Berry
0.17
Berry
0.17
Ãłn
0.16
anni
0.15
vik
0.15
_CLOCK
0.14
orie
0.14
æŁĦ
0.14
assin
0.14
ous
0.14
Activations Density 0.008%