INDEX

Explanations

a mix of abbreviations and numbers

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

))))

-0.57

))

-0.56

<eos>

-0.54

 ligiloj

-0.54

↵↵↵

-0.53

)))))

-0.53

 nakalista

-0.52

-0.51

</blockquote>

-0.50

 ExecuteAsync

-0.50

POSITIVE LOGITS

 Monfieur

0.91

 myſelf

0.88

ItemBackground

0.85

 itſelf

0.82

 Theſe

0.82

Efq

0.82

 Houſe

0.80

 Jefus

0.79

 ſeveral

0.79

 Chrift

0.78

Activations Density 0.987%