INDEX
Explanations
expressions highlighting the concept of love and relationships
New Auto-Interp
Negative Logits
Datuak
-1.13
decembrie
-0.76
ؤلاء
-0.76
Пусть
-0.68
noiembrie
-0.66
Wheeler
-0.65
tioners
-0.64
ویکیپدیای
-0.63
daz
-0.63
};
-0.62
POSITIVE LOGITS
love
1.80
LOVE
1.69
LOVE
1.61
Love
1.58
Love
1.50
loves
1.49
love
1.48
loves
1.41
Loves
1.41
loving
1.38
Activations Density 0.043%