INDEX
Explanations
references to community involvement and social cohesion
New Auto-Interp
Negative Logits
deaux
-0.16
linger
-0.15
ibel
-0.15
ãĥĥãĤ«ãĥ¼
-0.15
ookies
-0.14
__[
-0.14
ëŁī
-0.14
одо
-0.14
plat
-0.14
köln
-0.14
POSITIVE LOGITS
ικα
0.15
Peninsula
0.14
983
0.14
/local
0.14
åĺ
0.14
Polit
0.14
norm
0.14
grille
0.13
/community
0.13
onn
0.13
Activations Density 0.047%