INDEX
Explanations
mentions of people and their interactions
New Auto-Interp
Head Attr Weights
0:0.05
1:0.03
2:0.04
3:0.07
4:0.05
5:0.17
6:0.05
7:0.03
8:0.06
9:0.10
10:0.15
11:0.14
Negative Logits
esson
-1.26
ゴン
-1.22
motto
-1.19
®
-1.18
inka
-1.18
Grail
-1.17
polygamy
-1.17
slogan
-1.12
ceremony
-1.11
chu
-1.09
POSITIVE LOGITS
benefit
1.24
ividual
1.21
Avg
1.21
associations
1.19
soDeliveryDate
1.18
Puzzles
1.16
ices
1.12
thumbnails
1.11
randomized
1.10
NetMessage
1.10
Activations Density 0.077%