INDEX
Explanations
political news stories related to different regions and themes
topics related to political and LGBTQ+ news
New Auto-Interp
Negative Logits
cknowled
-0.68
Liberties
-0.59
Reviewer
-0.55
ère
-0.55
actionGroup
-0.54
aves
-0.54
thora
-0.53
acknowled
-0.52
sovere
-0.52
tolerate
-0.52
POSITIVE LOGITS
news
0.76
stories
0.59
stories
0.56
entimes
0.55
dash
0.53
Eye
0.53
Eva
0.53
impact
0.53
jury
0.52
notes
0.52
Activations Density 0.082%