INDEX
Explanations
references to birthdays and their celebrations
New Auto-Interp
Head Attr Weights
0:0.01
1:0.02
2:0.08
3:0.06
4:0.12
5:0.02
6:0.02
7:0.24
8:0.04
9:0.03
10:0.16
11:0.13
Negative Logits
effic
-1.49
marketplace
-1.49
mouths
-1.43
mouth
-1.38
videos
-1.36
ricular
-1.34
urches
-1.32
ramid
-1.32
environments
-1.31
asive
-1.27
POSITIVE LOGITS
cember
1.49
Dmit
1.29
birthday
1.29
NULL
1.27
iversary
1.27
laughter
1.25
anniversary
1.23
FontSize
1.21
................................................................
1.21
>[
1.19
Activations Density 0.006%