INDEX
Explanations
direct quotes or speech from individuals
New Auto-Interp
Negative Logits
ohl
-0.17
pt
-0.15
atham
-0.15
essim
-0.14
otti
-0.14
awai
-0.14
tainment
-0.14
uggy
-0.14
tar
-0.13
alytics
-0.13
POSITIVE LOGITS
inea
0.15
lund
0.15
ÂŃn
0.14
idth
0.14
anzi
0.13
chine
0.13
cen
0.13
379
0.13
_revision
0.13
stell
0.13
Activations Density 0.026%