INDEX
Explanations
references to love and relationships, especially in the context of arranged marriages and societal norms
New Auto-Interp
Negative Logits
íķĺìĭľ
-0.16
NSNotification
-0.15
Ethnic
-0.14
îł
-0.14
avier
-0.14
ÙħاÙĨÛĮ
-0.14
sse
-0.14
ÅĻeh
-0.14
é»Ħ
-0.13
ész
-0.13
POSITIVE LOGITS
arranged
0.39
dow
0.37
poly
0.30
Dow
0.28
arrange
0.26
arr
0.24
bride
0.23
Poly
0.23
Arrange
0.23
poly
0.23
Activations Density 0.426%