INDEX
Explanations
names of individuals, potentially related to politics or legal matters
named individuals and notable figures, particularly in a political context
New Auto-Interp
Negative Logits
ciating
-0.95
ablishment
-0.81
eals
-0.81
unres
-0.80
hof
-0.78
ican
-0.78
emonium
-0.77
cart
-0.77
erved
-0.76
otle
-0.76
POSITIVE LOGITS
é¾
0.82
vibrations
0.76
McCabe
0.74
Typhoon
0.73
shaw
0.70
Clifford
0.66
ministic
0.64
Sweeney
0.63
prope
0.63
apy
0.62
Activations Density 0.028%