INDEX
Explanations
phrases indicating membership or affiliation with organizations or groups
New Auto-Interp
Negative Logits
idavit
-0.72
HasBeenSet
-0.59
HashCode
-0.56
ocardio
-0.55
plained
-0.55
hashCode
-0.53
styleType
-0.53
atoon
-0.53
cillors
-0.52
Insee
-0.51
POSITIVE LOGITS
member
2.21
Member
2.05
Member
1.90
MEMBER
1.87
member
1.81
MEMBER
1.69
Mitglied
1.30
membro
1.21
miembro
1.16
membre
1.15
Activations Density 0.118%