INDEX
Explanations
political entities and their relationships
New Auto-Interp
Negative Logits
azer
-0.16
bus
-0.15
Crew
-0.14
crew
-0.14
vio
-0.14
fixture
-0.14
Ott
-0.14
Nev
-0.14
Charm
-0.14
lay
-0.13
POSITIVE LOGITS
anza
0.17
oba
0.16
orr
0.15
onia
0.15
otel
0.14
ctp
0.14
imest
0.14
anka
0.14
elman
0.14
ostel
0.14
Activations Density 0.002%