INDEX
Explanations
statements regarding political and social issues
New Auto-Interp
Negative Logits
phin
-0.15
aines
-0.15
ones
-0.14
æĬľ
-0.14
elize
-0.14
ácil
-0.14
emey
-0.14
instanc
-0.14
celik
-0.14
oader
-0.14
POSITIVE LOGITS
311
0.15
unspecified
0.15
Laur
0.15
èį
0.14
SPDX
0.14
rie
0.14
McCoy
0.14
fruit
0.13
multip
0.13
intern
0.13
Activations Density 1.040%