INDEX

Explanations

code-related terms like libraries, utilities, config, and exceptions

code, config, and utils

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

-0.50

↵↵

-0.48

Gu

-0.48

“

-0.47

</blockquote>

-0.46

non

-0.45

-0.42

POSITIVE LOGITS

 myſelf

1.11

 itſelf

1.06

Efq

1.04

 Monfieur

0.93

 himſelf

0.93

 doubtnut

0.92

 Theſe

0.90

 photolibrary

0.89

 Cæsar

0.87

BibitemShut

0.87

Activations Density 1.335%