INDEX
Explanations
punctuation, specifically commas
New Auto-Interp
Head Attr Weights
0:0.07
1:0.08
2:0.07
3:0.09
4:0.06
5:0.08
6:0.07
7:0.08
8:0.07
9:0.09
10:0.08
11:0.09
Negative Logits
Gins
-2.27
Quarterly
-2.12
Eliot
-2.10
Exhibit
-2.09
offic
-2.01
embod
-1.90
Doe
-1.86
Sally
-1.86
mourning
-1.85
recalling
-1.81
POSITIVE LOGITS
Minecraft
2.35
tek
2.26
魔
2.23
========
2.22
�
2.13
dict
2.10
cmd
2.08
�
2.07
PATH
2.02
�
1.99
Activations Density 0.000%