INDEX
Explanations
phrases related to governance and political issues
New Auto-Interp
Negative Logits
veis
-0.15
egment
-0.15
reetings
-0.14
.pth
-0.14
vastly
-0.14
phia
-0.14
ALSE
-0.14
nuest
-0.13
akis
-0.13
bai
-0.13
POSITIVE LOGITS
inux
0.16
scription
0.15
ERIC
0.15
Wand
0.14
rupa
0.14
659
0.14
oulos
0.14
º
0.14
408
0.14
.inline
0.14
Activations Density 0.001%