INDEX
Explanations
phrases mentioning "The New York Times"
mentions of "The New York Times."
New Auto-Interp
Negative Logits
ardless
-0.81
tesy
-0.80
reating
-0.79
icides
-0.76
ressive
-0.75
dyl
-0.72
razil
-0.71
peat
-0.71
ded
-0.70
rals
-0.70
POSITIVE LOGITS
bestselling
0.88
Square
0.87
Magazine
0.87
Newsp
0.80
Syndicate
0.80
Literary
0.79
Newspaper
0.79
Publishing
0.77
Dispatch
0.75
Corpus
0.75
Activations Density 0.016%