INDEX
Explanations
acknowledgement or affirmation
New Auto-Interp
Negative Logits
includes
0.36
however
0.34
alongside
0.32
jedoch
0.31
における
0.31
incorporates
0.30
comprises
0.30
lotions
0.30
polymers
0.30
during
0.29
POSITIVE LOGITS
Yeah
0.47
Yeah
0.47
Yes
0.46
হ্যাঁ
0.44
yeah
0.44
yeah
0.42
Definitely
0.41
yes
0.41
Yes
0.40
That
0.39
Activations Density 0.054%