INDEX
Explanations
Twitter handles and publication timestamps
New Auto-Interp
Negative Logits
iphy
-0.16
iability
-0.15
bulk
-0.15
Bulk
-0.15
anian
-0.15
_bulk
-0.15
Gab
-0.14
Nej
-0.14
Appeal
-0.14
ounc
-0.14
POSITIVE LOGITS
owitz
0.15
AMED
0.15
ableObject
0.15
izada
0.14
(od
0.14
shape
0.14
verg
0.13
дам
0.13
hire
0.13
ymax
0.13
Activations Density 0.043%