INDEX
Explanations
references to Catholic organizations and their activities
New Auto-Interp
Negative Logits
ert
-0.18
hw
-0.16
orb
-0.16
ẫ
-0.15
jar
-0.15
edReader
-0.15
rowned
-0.15
екаÑĢ
-0.14
heets
-0.14
ertation
-0.14
POSITIVE LOGITS
ism
0.25
ity
0.23
å¾Ĵ
0.22
ical
0.20
osate
0.19
idad
0.18
Worker
0.18
Church
0.17
-major
0.17
/non
0.16
Activations Density 0.010%