INDEX
Explanations
references to cultural heritage and familial relationships
New Auto-Interp
Negative Logits
&&
-0.74
并且
-0.70
serta
-0.70
&&(
-0.63
그리고
-0.62
且
-0.60
sowie
-0.58
-,
-0.57
并
-0.57
、
-0.57
POSITIVE LOGITS
noDo
0.51
OGND
0.49
للمعارف
0.48
Drapeau
0.43
Rüyada
0.43
ۖ
0.43
ۗ
0.43
kmäler
0.43
DockStyle
0.43
Спасылкі
0.42
Activations Density 1.031%