INDEX
Explanations
terminologies related to legal processes and concepts
New Auto-Interp
Negative Logits
↵
-1.29
↵↵
-0.96
<eos>
-0.90
[…]
-0.87
↵↵↵
-0.72
-0.58
↵↵↵↵
-0.57
-0.50
...
-0.50
↵↵↵↵↵
-0.50
POSITIVE LOGITS
+#+
1.03
^(@)
0.96
raiſ
0.91
purpoſe
0.90
ConstraintMaker
0.90
Monfieur
0.89
houſe
0.89
―――――
0.89
Anſ
0.88
ſche
0.88
Activations Density 2.161%