INDEX
Explanations
actions/roles/system details
New Auto-Interp
Negative Logits
brownies
0.41
widths
0.41
ligere
0.39
territoires
0.39
energije
0.39
pairs
0.38
engkap
0.38
тела
0.38
energético
0.38
gerais
0.38
POSITIVE LOGITS
دریافت
0.49
receive
0.46
ontvang
0.41
وقتی
0.41
written
0.39
angu
0.39
когда
0.39
показа
0.39
することも
0.38
отра
0.38
Activations Density 0.002%