INDEX

Explanations

A-docket numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 additional

-1.67

 actually

-1.35

so

-1.31

 also

-1.26

or

-1.23

to

-1.23

 compagni

-1.22

 adding

-1.19

 other

-1.17

it

-1.14

POSITIVE LOGITS

歺

1.63

Their

1.38

 ihrer

1.36

 DELHI

1.34

 ihrem

1.33

푉

1.31

 représenter

1.30

 Journalist

1.30

organised

1.28

 ihres

1.27

Activations Density 0.326%