INDEX
Explanations
mentions of the "First Amendment."
New Auto-Interp
Negative Logits
leur
-0.56
Pautan
-0.51
-0.49
general
-0.45
another
-0.44
popular
-0.41
A
-0.41
LayoutParams
-0.40
stopPropagation
-0.40
least
-0.40
POSITIVE LOGITS
First
1.63
First
1.46
Second
1.42
Third
1.36
Second
1.26
Third
1.18
Fourth
1.14
Fifth
1.13
Sixth
1.06
Ersten
1.05
Activations Density 0.149%