INDEX
Explanations
government and commercial urls
New Auto-Interp
Negative Logits
/',
1.31
/,
1.30
/",
1.26
/</
1.26
/,
1.24
/";
1.18
/[
1.13
/;
1.12
/';
1.12
/'
1.11
POSITIVE LOGITS
!!)
1.01
..)
0.99
...)
0.89
(""))0.88
!)
0.87
.)..
0.81
)..
0.77
="")
0.77
)=
0.77
…)
0.76
Activations Density 0.052%