INDEX
Negative Logits
Efq
-0.87
raiſ
-0.86
Monfieur
-0.86
ordinary
-0.84
pleaſure
-0.83
educated
-0.83
tranſ
-0.83
Eſ
-0.82
cauſe
-0.81
purpoſe
-0.80
POSITIVE LOGITS
}))
0.65
?')
0.63
}')
0.63
?")
0.62
>')
0.62
)));
0.61
ⓧ
0.60
}));
0.59
())));
0.59
__':
0.58
Activations Density 0.084%