INDEX
Explanations
words related to souvenirs and memorabilia
New Auto-Interp
Head Attr Weights
0:0.03
1:0.01
2:0.08
3:0.06
4:0.07
5:0.04
6:0.05
7:0.20
8:0.03
9:0.04
10:0.19
11:0.15
Negative Logits
hra
-1.44
waters
-1.33
blender
-1.25
obar
-1.23
irens
-1.20
Exec
-1.20
Morg
-1.19
Valhalla
-1.18
esson
-1.18
ragon
-1.17
POSITIVE LOGITS
heed
1.45
MK
1.39
captcha
1.31
"],"
1.28
ipeg
1.28
dues
1.27
intangible
1.26
abee
1.25
ritz
1.24
mailing
1.24
Activations Density 0.000%