INDEX

Explanations

mathematical expressions and comparisons

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

-1.52

 используют

-1.48

に対し

-1.38

怎么说

-1.37

wr

-1.34

↵↵

-1.34

⢊

-1.33

new

-1.32

については

-1.31

</strong>

-1.29

POSITIVE LOGITS

Мон

1.40

you

1.37

Можно

1.30

контро

1.30

it

1.30

çek

1.25

ÁN

1.23

ßten

1.22

Когда

1.21

кзак

1.20

Activations Density 0.011%