INDEX
Explanations
phrases related to legal processes and governmental procedures
statistical data and references to quantitative claims or observations
New Auto-Interp
Negative Logits
ubis
-0.75
ciplinary
-0.71
iris
-0.69
":[
-0.67
afety
-0.66
olerance
-0.64
Picture
-0.64
np
-0.63
Fn
-0.62
iage
-0.62
POSITIVE LOGITS
?).
1.26
?)
1.26
?),
1.22
)?
1.20
!)
1.17
!).
1.16
!),
1.13
)—
1.09
*)
1.09
)
1.08
Activations Density 1.129%