INDEX
Explanations
references to manufacturing and industrial sectors
New Auto-Interp
Head Attr Weights
0:0.04
1:0.01
2:0.06
3:0.06
4:0.05
5:0.05
6:0.06
7:0.04
8:0.03
9:0.06
10:0.29
11:0.22
Negative Logits
ACTIONS
-1.41
retweet
-1.22
afort
-1.16
Investig
-1.14
Detect
-1.14
tweets
-1.13
dismissing
-1.10
retract
-1.10
headset
-1.08
decriminal
-1.08
POSITIVE LOGITS
roup
1.37
orkshire
1.33
swick
1.30
occupations
1.25
archs
1.24
etc
1.23
essional
1.21
aeda
1.21
rons
1.21
groups
1.18
Activations Density 0.082%