INDEX
Explanations
mentions of specific names, particularly the name "Emily"
mentions of the name "Emily" and related names
New Auto-Interp
Negative Logits
lasses
-0.81
ername
-0.79
xual
-0.76
DragonMagazine
-0.73
stood
-0.71
nings
-0.71
nesses
-0.70
tenance
-0.69
nown
-0.66
ernel
-0.66
POSITIVE LOGITS
Dickinson
1.16
Lak
1.16
gdala
0.85
issance
0.81
otte
0.81
endi
0.78
gown
0.77
pton
0.73
Thorn
0.73
ãĤ£
0.72
Activations Density 0.034%