INDEX

Explanations

truth be told, said, known

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

is

-2.03

-1.40

bernador

-1.38

</h2>

-1.33

at

-1.29

-1.25

 conseguido

-1.24

ógicas

-1.23

in

-1.21

can

-1.19

POSITIVE LOGITS

英寸

1.41

⾦

1.34

ξεις

1.34

絝

1.32

 embora

1.30

個人的には

1.30

袛

1.30

看了一眼

1.30

 besos

1.29

 RECOMM

1.27

Activations Density 0.109%