INDEX
Explanations
references to specific individuals and their actions within the context of stories or reports
New Auto-Interp
Head Attr Weights
0:0.07
1:0.03
2:0.05
3:0.05
4:0.05
5:0.05
6:0.21
7:0.04
8:0.12
9:0.20
10:0.03
11:0.05
Negative Logits
charism
-3.47
Lann
-3.36
ascar
-3.33
urrencies
-3.28
evangel
-3.20
chrom
-3.20
gem
-3.15
Barcelona
-3.14
carbohydrate
-3.13
xual
-3.12
POSITIVE LOGITS
Lowell
7.87
Tacoma
7.80
Everett
7.78
verett
5.24
Pierce
4.80
Worcester
4.48
Morse
4.16
Naval
4.10
Frem
4.07
Dot
4.00
Activations Density 0.002%