INDEX
Explanations
numerical data and significant dates related to events or figures
New Auto-Interp
Head Attr Weights
0:0.04
1:0.02
2:0.12
3:0.10
4:0.02
5:0.18
6:0.04
7:0.03
8:0.06
9:0.21
10:0.09
11:0.03
Negative Logits
Translation
-1.05
frown
-1.01
pans
-1.01
emia
-1.00
favorites
-0.94
-0.93
indispensable
-0.93
Confederacy
-0.93
dialog
-0.93
conqu
-0.92
POSITIVE LOGITS
PsyNetMessage
1.40
confir
1.28
osures
1.28
wcs
1.26
ategory
1.24
ahon
1.24
acknow
1.21
ikers
1.19
vironment
1.18
EVA
1.17
Activations Density 0.166%