INDEX
Explanations
mentions of significant events or incidents occurring within a community context
New Auto-Interp
Head Attr Weights
0:0.06
1:0.04
2:0.08
3:0.07
4:0.03
5:0.13
6:0.03
7:0.04
8:0.07
9:0.30
10:0.07
11:0.04
Negative Logits
TTL
-1.41
antics
-1.37
AOL
-1.23
thood
-1.19
Cly
-1.17
Lifetime
-1.15
abolition
-1.15
folio
-1.15
autobiography
-1.14
thren
-1.14
POSITIVE LOGITS
contaminated
1.29
airst
1.25
protr
1.25
Guan
1.22
ambul
1.22
inson
1.20
piping
1.19
Sensor
1.17
Santiago
1.13
tyard
1.12
Activations Density 0.031%