INDEX
Explanations
financial terms, names of individuals often associated with politics or business, and specific brand names
references to political figures and entities
New Auto-Interp
Negative Logits
ingly
-0.84
Ĥ¬
-0.84
runners
-0.79
itives
-0.76
etry
-0.76
£ı
-0.76
Ł
-0.76
bley
-0.74
runner
-0.74
bing
-0.74
POSITIVE LOGITS
atinum
0.72
Carly
0.72
Surgery
0.70
insurer
0.69
Ducks
0.66
XVI
0.66
surgeons
0.65
Blanc
0.64
bourg
0.63
Clause
0.63
Activations Density 0.049%