INDEX

Explanations

mathematical expressions with parentheses

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

No Comments

Negative Logits

^(@)

-0.77

PyExc

-0.77

 photolibrary

-0.72

 ་་

-0.71

 ―――――

-0.68

Glej

-0.68

ArgumentParser

-0.67

)•

-0.66

̈́

-0.66

 lyre

-0.65

POSITIVE LOGITS

<eos>

0.49

ETHING

0.49

↵↵

0.48

 iNdEx

0.48

↵

0.47

The

0.46

 expanding

0.44

паль

0.44

0.43

Activations Density 0.008%