INDEX
Explanations
references to political donations and fundraising activities
New Auto-Interp
Negative Logits
UK
-0.21
incy
-0.19
otta
-0.18
alleged
-0.18
impacted
-0.17
userID
-0.17
allegedly
-0.17
WWII
-0.16
uum
-0.16
pics
-0.16
POSITIVE LOGITS
Mr
0.29
Ms
0.27
Qaeda
0.25
Mr
0.25
Ms
0.22
United
0.18
inus
0.17
GuidId
0.17
Mrs
0.16
United
0.16
Activations Density 0.122%