INDEX

Explanations

license disclaimers.

Code/Legal documents

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

 houſe

-0.81

 ſtate

-0.77

 purpoſe

-0.76

 ſta

-0.74

ſelf

-0.72

 themſelves

-0.71

 ſche

-0.71

 myſelf

-0.71

 ftate

-0.70

 kleid

-0.69

POSITIVE LOGITS

ni

0.51

gl

0.50

DoubleQuotes

0.49

ni

0.49

ua

0.49

Ei

0.49

gl

0.48

Bitpie

0.47

lo

0.47

va

0.47

Activations Density 1.753%