INDEX
Explanations
descriptive elements of items and their characteristics
New Auto-Interp
Negative Logits
perciò
-0.41
</i>
-0.41
[
-0.40
I
-0.39
[
-0.38
\\
-0.38
inderdaad
-0.36
&#
-0.35
[\
-0.34
Vle
-0.33
POSITIVE LOGITS
NameInMap
1.02
يكب
1.02
kasarigan
0.97
Vidite
0.91
تقاوى
0.88
cherchés
0.87
تضيفلها
0.87
Personendaten
0.86
+#+#
0.85
<eos>
0.84
Activations Density 0.094%