INDEX
Explanations
news articles related to legal issues and law enforcement
references to news sources and citations in articles
New Auto-Interp
Head Attr Weights
0:0.11
1:0.03
2:0.08
3:0.11
4:0.04
5:0.10
6:0.10
7:0.04
8:0.06
9:0.09
10:0.15
11:0.04
Negative Logits
etheless
-1.61
agnetic
-1.31
guiName
-1.19
ordable
-1.17
fml
-1.15
uggish
-1.11
within
-1.10
frac
-1.10
reated
-1.09
aneously
-1.07
POSITIVE LOGITS
.)
2.57
!)
2.42
.)
2.42
…)
2.39
?)
2.22
*)
2.18
.")
2.17
,)
2.12
!),
2.11
?)
2.06
Activations Density 0.111%