INDEX
Explanations
references to U.S. government and military actions or policies
New Auto-Interp
Head Attr Weights
0:0.03
1:0.03
2:0.07
3:0.06
4:0.02
5:0.05
6:0.24
7:0.23
8:0.07
9:0.03
10:0.07
11:0.04
Negative Logits
tein
-1.31
ksh
-1.18
Ping
-1.04
ke
-1.04
inbox
-0.99
folders
-0.99
Void
-0.99
plush
-0.97
alg
-0.97
random
-0.96
POSITIVE LOGITS
rican
1.45
consulate
1.35
diplomat
1.23
glers
1.20
insured
1.15
overseas
1.11
annex
1.10
assies
1.09
ambassador
1.08
carrier
1.07
Activations Density 0.080%