INDEX
Explanations
references to significant political events or announcements
New Auto-Interp
Negative Logits
abeth
-0.17
onas
-0.17
OPSIS
-0.15
etto
-0.14
conciliation
-0.14
comed
-0.14
}->
-0.14
Spicer
-0.14
statt
-0.14
vero
-0.14
POSITIVE LOGITS
oux
0.16
yal
0.15
Ass
0.15
igor
0.15
Dec
0.15
piger
0.14
elen
0.14
udu
0.14
ãģ²ãģ¨
0.14
hab
0.14
Activations Density 0.170%