INDEX
Explanations
names, especially the name "Ariel"
mentions of specific names or entities
New Auto-Interp
Negative Logits
arnaev
-0.83
opia
-0.75
opal
-0.75
alm
-0.74
alore
-0.74
stakes
-0.73
urally
-0.72
ulhu
-0.72
under
-0.71
ongyang
-0.70
POSITIVE LOGITS
Ariel
1.09
Sharon
0.95
Levy
0.80
Zamb
0.79
Atom
0.78
Gord
0.78
Gru
0.77
Castro
0.73
Zur
0.70
Luna
0.70
Activations Density 0.013%