INDEX

Explanations

words and phrases used in legal arguments

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GenerationType

-0.87

TRIBUT

-0.68

 ostavi

-0.65

expandindo

-0.65

WithMany

-0.64

 memoized

-0.61

multer

-0.59

memoized

-0.59

 fortemente

-0.59

sidemargin

-0.58

POSITIVE LOGITS

 correct

1.58

 proper

1.52

 properly

1.42

Proper

1.42

 PROPER

1.41

 correcte

1.39

 Proper

1.37

 accurate

1.35

 adequate

1.35

 appropriate

1.34

Activations Density 3.807%