INDEX
Explanations
mentions of political figures and their associated events or actions
New Auto-Interp
Negative Logits
:✨
-0.58
nobre
-0.40
öne
-0.37
bahía
-0.37
ricco
-0.37
fotografico
-0.37
naturen
-0.37
esportivo
-0.36
Tembelea
-0.35
lingue
-0.34
POSITIVE LOGITS
esque
0.88
isms
0.77
wanna
0.75
clones
0.69
esque
0.67
ian
0.66
Effect
0.66
mania
0.65
Appreciation
0.65
style
0.64
Activations Density 0.767%