INDEX

Explanations

code return type hints

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

 seem

-1.05

子さん

-1.02

 darüber

-0.91

問合せ

-0.87

行く

-0.87

づけ

-0.84

cryption

-0.84

 IllegalArgument

-0.83

way

-0.83

 Reichs

-0.83

POSITIVE LOGITS

1.33

|\

1.30

|$

1.23

↵

1.22

 returns

1.15

</h3>

1.13

</h2>

1.10

|}

1.09

returns

1.09

返回

1.06

Activations Density 0.005%