INDEX
Explanations
references to religious institutions and their affiliations
New Auto-Interp
Negative Logits
egg
-0.19
Citizen
-0.16
ibbon
-0.16
oa
-0.16
ilha
-0.15
Dial
-0.15
vale
-0.15
íĥ
-0.15
Jehovah
-0.15
568
-0.14
POSITIVE LOGITS
Lamb
0.31
Province
0.25
Canterbury
0.24
Province
0.24
Prim
0.23
Syn
0.22
++
0.21
prim
0.21
di
0.20
Row
0.20
Activations Density 0.029%