INDEX
Explanations
proper nouns associated with a particular political party
mentions of the political party "Greens."
New Auto-Interp
Negative Logits
bred
-0.74
ALLY
-0.64
ufact
-0.63
ographed
-0.60
xus
-0.59
bron
-0.58
nce
-0.58
Epstein
-0.57
cv
-0.57
Wan
-0.57
POSITIVE LOGITS
boro
1.27
auld
0.92
wich
0.90
ync
0.88
reens
0.87
aby
0.85
burg
0.85
pace
0.85
borg
0.83
peace
0.81
Activations Density 0.013%