INDEX
Explanations
references to significant statements and opinions
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.16
3:0.06
4:0.15
5:0.03
6:0.06
7:0.05
8:0.06
9:0.05
10:0.10
11:0.18
Negative Logits
advoc
-1.26
idates
-1.17
Introduced
-1.07
Hait
-1.06
guiIcon
-1.06
ratulations
-1.05
mention
-1.04
Ket
-1.03
umbn
-1.02
undown
-1.00
POSITIVE LOGITS
ammy
1.32
pload
1.27
tighter
1.24
TPPStreamerBot
1.21
orrow
1.18
1.18
nor
1.09
wolf
1.09
irth
1.08
worn
1.07
Activations Density 0.053%