INDEX
Explanations
references to various animals and creatures, particularly those associated with fantastical or horror themes
New Auto-Interp
Head Attr Weights
0:0.11
1:0.04
2:0.06
3:0.04
4:0.04
5:0.09
6:0.16
7:0.09
8:0.04
9:0.05
10:0.16
11:0.07
Negative Logits
WRITE
-1.40
UNCLASSIFIED
-1.29
heit
-1.29
ATIVE
-1.24
EMBER
-1.21
ICA
-1.17
)=(
-1.17
ÍÍ
-1.16
Fiscal
-1.15
CLASSIFIED
-1.14
POSITIVE LOGITS
fish
1.26
erker
1.22
hunter
1.19
hun
1.18
argon
1.18
azo
1.17
claw
1.14
guard
1.14
bane
1.13
ˈ
1.13
Activations Density 0.170%