INDEX
Explanations
names and surnames
mentions of specific individuals, particularly those with the last name 'Heller' or 'Keller'
New Auto-Interp
Negative Logits
orough
-0.83
ashington
-0.73
————————
-0.73
Es
-0.71
nie
-0.68
reon
-0.66
emale
-0.66
olitan
-0.64
eday
-0.63
arching
-0.62
POSITIVE LOGITS
gren
0.91
anguage
0.87
ĨĴ
0.82
onom
0.78
ounge
0.78
wagen
0.77
gang
0.76
ifice
0.76
onica
0.75
bach
0.75
Activations Density 0.034%