INDEX
Explanations
references to specific individuals or organizations
New Auto-Interp
Head Attr Weights
0:0.02
1:0.04
2:0.05
3:0.26
4:0.02
5:0.02
6:0.12
7:0.10
8:0.04
9:0.12
10:0.05
11:0.10
Negative Logits
keyes
-1.25
EH
-1.22
ggle
-1.09
\\\\\\\\
-1.07
ulhu
-1.07
scientific
-1.06
miah
-1.05
study
-1.03
AppData
-1.03
iculture
-1.02
POSITIVE LOGITS
earances
1.31
ttes
1.22
Absent
1.12
IMAGES
1.11
Vaj
1.09
Frey
1.08
handcuffs
1.06
ollah
1.06
Shares
1.05
entin
1.03
Activations Density 0.001%