INDEX
Explanations
claims related to human rights and social justice
New Auto-Interp
Head Attr Weights
0:0.04
1:0.03
2:0.04
3:0.12
4:0.04
5:0.09
6:0.03
7:0.02
8:0.04
9:0.19
10:0.20
11:0.11
Negative Logits
strang
-1.46
bogus
-1.41
anyway
-1.31
phony
-1.27
behav
-1.27
goof
-1.24
dangling
-1.24
Fake
-1.24
subter
-1.23
$$$$
-1.20
POSITIVE LOGITS
osponsors
1.32
consultation
1.26
welcomes
1.23
Reviews
1.21
2020
1.20
Diversity
1.19
Cosponsors
1.18
Updated
1.16
ibilities
1.15
Lessons
1.15
Activations Density 1.197%