INDEX
Explanations
sequences of characters or letter patterns that resemble phonetic sounds
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.05
3:0.06
4:0.04
5:0.05
6:0.45
7:0.03
8:0.05
9:0.06
10:0.07
11:0.04
Negative Logits
vp
-1.36
specificity
-1.21
setbacks
-1.21
immersion
-1.21
spoilers
-1.19
advertisers
-1.19
exaggeration
-1.19
srfAttach
-1.16
involvement
-1.13
eele
-1.13
POSITIVE LOGITS
atra
1.44
idas
1.40
adelphia
1.38
lich
1.23
nant
1.23
ebook
1.21
aign
1.21
gypt
1.20
zai
1.20
deck
1.19
Activations Density 0.008%