INDEX

Explanations

restriction, limiting actions

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wy

-0.77

 Majefty

-0.71

 Merit

-0.68

 merit

-0.66

 виправивши

-0.63

 Anſ

-0.62

ſy

-0.62

 themſelves

-0.61

 iſt

-0.60

 Theſe

-0.59

POSITIVE LOGITS

########.

0.71

 lệ

0.63

0.61

:✨

0.54

unk

0.54

DoubleQuotes

0.53

 rzecz

0.52

ers

0.51

verwijspagina

0.49

Activations Density 0.552%