INDEX
Explanations
references to the city of New York
mentions of New York City
New Auto-Interp
Negative Logits
TPP
-0.86
EMP
-0.84
wcsstore
-0.80
milo
-0.78
VPN
-0.78
cend
-0.73
vol
-0.73
kick
-0.71
selection
-0.71
unct
-0.71
POSITIVE LOGITS
City
1.22
Mellon
1.03
Harbor
0.96
Times
0.86
Cosmos
0.84
Giants
0.83
State
0.82
Knicks
0.82
Yankees
0.80
skyline
0.78
Activations Density 0.030%