INDEX
Explanations
references to specific literary works and their thematic significance
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.08
3:0.25
4:0.02
5:0.02
6:0.15
7:0.10
8:0.03
9:0.05
10:0.06
11:0.12
Negative Logits
destiny
-1.26
intermedi
-1.20
destination
-1.17
slope
-1.11
itory
-1.10
delim
-1.07
redes
-1.06
channel
-1.04
omission
-1.04
lesson
-1.04
POSITIVE LOGITS
arella
1.41
ゼウス
1.38
elli
1.36
Manson
1.30
tics
1.24
coni
1.23
ucc
1.22
Greg
1.18
Dick
1.18
Glass
1.16
Activations Density 0.002%