INDEX
Explanations
mentions of the city of Berkeley
mentions of the city or institution of Berkeley
New Auto-Interp
Negative Logits
ions
-0.79
icate
-0.69
itaire
-0.68
ive
-0.66
marks
-0.66
reconc
-0.64
marked
-0.64
folio
-0.63
Cherokee
-0.63
orship
-0.62
POSITIVE LOGITS
Yiannopoulos
0.87
keley
0.78
âĨij
0.77
Milo
0.72
Berkeley
0.68
ãĥ£
0.68
Mom
0.65
mare
0.63
llor
0.63
Fiorina
0.63
Activations Density 0.069%