INDEX
Explanations
occurrences of fractions or ratios
New Auto-Interp
Head Attr Weights
0:0.24
1:0.11
2:0.02
3:0.04
4:0.05
5:0.10
6:0.14
7:0.01
8:0.07
9:0.07
10:0.03
11:0.06
Negative Logits
tnc
-1.93
mars
-1.64
Cong
-1.53
adelphia
-1.51
hens
-1.47
HH
-1.42
DON
-1.41
ONES
-1.41
christ
-1.41
Columbia
-1.39
POSITIVE LOGITS
�
2.21
�
2.18
�
2.08
�
1.95
�
1.94
�
1.89
�
1.86
�
1.86
�
1.83
�
1.82
Activations Density 0.002%