INDEX
Explanations
mentions of a particular individual's name
references to specific individuals, particularly those associated with news or media
New Auto-Interp
Negative Logits
kson
-0.78
pmwiki
-0.69
BP
-0.68
iders
-0.68
imen
-0.67
Catalog
-0.66
itable
-0.65
mington
-0.65
uton
-0.65
Page
-0.63
POSITIVE LOGITS
į
0.92
ĵĺ
0.90
Ĩ
0.90
ļé
0.86
Ħ
0.84
lain
0.81
Ľ
0.78
ı
0.78
artisan
0.77
ĪĴ
0.77
Activations Density 0.030%