INDEX
Explanations
mentions of a specific political party named "Greens" with varying levels of relevance
references to the Greens political party
New Auto-Interp
Negative Logits
ufact
-0.72
ographed
-0.66
bred
-0.66
ALLY
-0.65
aneously
-0.62
istically
-0.62
ãĥį
-0.61
Buc
-0.57
xus
-0.55
Wan
-0.55
POSITIVE LOGITS
boro
1.29
wich
0.97
auld
0.93
burg
0.91
aby
0.85
ync
0.83
pun
0.82
borg
0.82
pan
0.81
pire
0.80
Activations Density 0.013%