INDEX
Explanations
mentions of the institution "Columbia University"
references to Columbia University
New Auto-Interp
Negative Logits
esthetic
-0.79
cher
-0.77
visor
-0.76
stay
-0.73
chers
-0.73
hered
-0.69
pora
-0.68
\<
-0.67
nesses
-0.66
TY
-0.66
POSITIVE LOGITS
Heights
1.05
River
0.93
Pictures
0.90
Colleges
0.81
Journalism
0.81
Gorge
0.80
Pike
0.79
Canal
0.78
Broadcasting
0.78
University
0.75
Activations Density 0.037%