INDEX
Explanations
references to the city of Philadelphia
mentions of the city of Philadelphia
New Auto-Interp
Negative Logits
cream
-0.81
Xie
-0.73
axes
-0.73
aid
-0.71
hai
-0.71
ui
-0.71
licences
-0.71
armour
-0.69
subtitles
-0.69
Carbuncle
-0.69
POSITIVE LOGITS
Philadelphia
3.55
Philadelphia
3.37
Philly
3.02
Pittsburgh
2.18
Baltimore
1.99
Pennsylvania
1.97
Atlanta
1.93
Chicago
1.88
Cleveland
1.86
Newark
1.85
Activations Density 0.021%