INDEX
Explanations
capitalized acronyms and proper nouns
New Auto-Interp
Head Attr Weights
0:0.02
1:0.01
2:0.05
3:0.06
4:0.05
5:0.03
6:0.48
7:0.03
8:0.04
9:0.06
10:0.06
11:0.06
Negative Logits
��
-1.43
Û
-1.36
�
-1.27
REC
-1.25
�
-1.24
autop
-1.24
URA
-1.23
gyn
-1.22
PDATE
-1.21
thous
-1.21
POSITIVE LOGITS
ividual
1.21
settles
1.21
seizures
1.19
igham
1.19
ibaba
1.19
��
1.18
morph
1.18
Islands
1.17
earances
1.17
chew
1.17
Activations Density 0.004%