INDEX
Explanations
terms related to societal structures and impacts of policies
New Auto-Interp
Head Attr Weights
0:0.05
1:0.08
2:0.14
3:0.06
4:0.03
5:0.03
6:0.12
7:0.13
8:0.11
9:0.04
10:0.10
11:0.06
Negative Logits
Invention
-1.25
sidx
-1.20
ozo
-1.13
utterstock
-1.12
bilt
-1.08
imester
-1.05
iky
-1.04
mone
-1.04
intendo
-1.04
urnal
-1.03
POSITIVE LOGITS
ages
1.21
exists
1.14
plays
1.08
should
1.08
alike
1.06
grades
1.03
Moscow
1.02
hadn
1.01
MPEG
1.01
ises
0.99
Activations Density 0.287%