INDEX
Explanations
references to social and religious divisions within communities
New Auto-Interp
Negative Logits
857
-0.18
799
-0.16
862
-0.15
982
-0.14
Evangel
-0.14
.INSTANCE
-0.13
bapt
-0.13
Lutheran
-0.13
æĹ
-0.13
"class
-0.13
POSITIVE LOGITS
ãĤ«ãĥ¼
0.14
RAND
0.14
Cres
0.14
jug
0.14
ÃĤu
0.14
ÑģоÑĤ
0.14
Lâm
0.14
Ø¡
0.13
slaught
0.13
htaking
0.13
Activations Density 0.025%