INDEX
Explanations
keywords related to local governance and community events
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.12
3:0.25
4:0.01
5:0.02
6:0.22
7:0.09
8:0.04
9:0.04
10:0.08
11:0.04
Negative Logits
romeda
-1.30
metast
-1.24
aciously
-1.23
clone
-1.21
'?
-1.18
comings
-1.15
.�
-1.14
cells
-1.14
selves
-1.13
ilogy
-1.11
POSITIVE LOGITS
Execution
1.34
Shoes
1.25
Sharia
1.24
haus
1.24
Loud
1.23
Mal
1.23
Bak
1.22
Abyss
1.21
Own
1.20
Az
1.20
Activations Density 0.274%