INDEX
Explanations
mentions of parties and related events
New Auto-Interp
Negative Logits
lest
-0.19
mel
-0.18
stone
-0.18
most
-0.16
erness
-0.15
amped
-0.15
ociety
-0.15
aghan
-0.15
parties
-0.15
eref
-0.15
POSITIVE LOGITS
ing
0.22
go
0.21
Fav
0.19
wide
0.19
time
0.18
AGMA
0.16
tura
0.16
animals
0.15
icular
0.15
oons
0.15
Activations Density 0.032%