INDEX
Negative Logits
juga
0.81
मानी
0.80
कैसी
0.79
perceives
0.78
looks
0.77
sooo
0.77
seems
0.75
symbolizes
0.75
sempre
0.75
exciting
0.74
POSITIVE LOGITS
speaking
1.12
speaking
1.05
Speaking
1.00
Speaking
0.99
Worse
0.88
Thankfully
0.88
хуже
0.87
where
0.83
newcomers
0.82
where
0.80
Activations Density 0.013%