INDEX
Explanations
references to data, statistics, or notable software within a context
New Auto-Interp
Head Attr Weights
0:0.03
1:0.03
2:0.07
3:0.07
4:0.03
5:0.04
6:0.12
7:0.35
8:0.06
9:0.03
10:0.07
11:0.04
Negative Logits
ilst
-1.35
wcsstore
-1.31
isSpecialOrderable
-1.28
ItemImage
-1.25
kat
-1.24
natureconservancy
-1.24
Indian
-1.23
�
-1.19
Aim
-1.19
occup
-1.19
POSITIVE LOGITS
Canaver
1.41
swallowed
1.22
Rockefeller
1.20
psy
1.19
Pru
1.14
Spock
1.09
Psy
1.09
umping
1.08
1924
1.07
onics
1.07
Activations Density 0.079%