INDEX
Explanations
terms related to legal proceedings and jury activities
New Auto-Interp
Head Attr Weights
0:0.03
1:0.01
2:0.07
3:0.05
4:0.06
5:0.04
6:0.35
7:0.04
8:0.03
9:0.04
10:0.18
11:0.06
Negative Logits
uala
-1.44
ForgeModLoader
-1.34
href
-1.32
pedd
-1.31
achev
-1.29
compan
-1.26
Virtue
-1.26
entimes
-1.25
unman
-1.25
rast
-1.24
POSITIVE LOGITS
ointed
1.51
Suns
1.43
ices
1.40
Sparks
1.36
unanimous
1.28
reciation
1.25
inches
1.25
swer
1.24
sent
1.20
blow
1.19
Activations Density 0.001%