INDEX
Explanations
mentions of popular entertainment figures and their impact on the author
New Auto-Interp
Negative Logits
orex
-0.16
431
-0.16
ipes
-0.16
479
-0.15
aleb
-0.14
juan
-0.14
ollections
-0.13
489
-0.13
Competitive
-0.13
_CI
-0.13
POSITIVE LOGITS
whom
0.17
rahim
0.15
ey
0.14
nid
0.14
barr
0.14
ÑıÑĤ
0.14
assi
0.14
nr
0.14
ikler
0.14
aller
0.13
Activations Density 0.084%