INDEX
Explanations
references to specific substances or medications
New Auto-Interp
Head Attr Weights
0:0.03
1:0.06
2:0.09
3:0.18
4:0.05
5:0.04
6:0.08
7:0.14
8:0.06
9:0.08
10:0.06
11:0.08
Negative Logits
llor
-1.31
iets
-1.13
ruit
-1.08
ugi
-1.07
rider
-1.06
arios
-1.05
Objective
-1.04
lich
-1.03
crafts
-1.03
Keefe
-1.03
POSITIVE LOGITS
*/(
1.49
pload
1.35
Thumbnails
1.33
intangible
1.28
Cosponsors
1.23
slightest
1.19
ancial
1.17
endment
1.11
anship
1.09
perture
1.09
Activations Density 0.004%