INDEX

Explanations

code snippets or markup

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

parian

-1.38

 имеют

-1.32

 mehrm

-1.32

 هنوز

-1.32

 generado

-1.31

 geralmente

-1.26

 включает

-1.26

めっちゃ

-1.23

Cg

-1.23

 hergestellt

-1.23

POSITIVE LOGITS

 more

1.65

at

1.64

if

1.59

as

1.46

by

1.41

any

1.34

 this

1.30

 such

1.28

now

1.27

 puasa

1.26

Activations Density 0.006%