INDEX
Explanations
interrogative phrases and questions
New Auto-Interp
Negative Logits
greateſt
-0.93
Geplaatst
-0.87
kasarigan
-0.84
itſelf
-0.83
<?
-0.80
pleaſure
-0.79
ſelves
-0.79
་་
-0.77
становника
-0.76
Савезне
-0.76
POSITIVE LOGITS
Does
0.89
האם
0.87
apakah
0.87
Is
0.85
Does
0.80
whether
0.78
Is
0.77
آیا
0.77
هل
0.77
Apakah
0.72
Activations Density 0.146%