INDEX

Explanations

code comment metadata authors

colons in code metadata, annotations, and documentation (such as in author tags, file headers, and decorator syntax).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 ordentlich

-1.66

旅遊

-1.64

 个性

-1.61

ﾞ

-1.59

</em>

-1.59

 宣传

-1.57

 хто

-1.54

 llanto

-1.52

 larmes

-1.52

snd

-1.52

POSITIVE LOGITS

</h1>

2.19

but

1.82

’

1.69

and

1.68

if

1.63

you

1.54

 this

1.52

udere

1.48

 mark

1.46

 misi

1.43

Activations Density 0.027%