INDEX

Explanations

type literals and punctuation

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

 även

-0.99

 otros

-0.97

autres

-0.91

 other

-0.85

 incor

-0.85

/");

-0.85

diq

-0.84

贋

-0.83

Obstacle

-0.82

 теперь

-0.80

POSITIVE LOGITS

 itself

1.30

 Itself

0.90

is

0.90

itself

0.88

 themselves

0.85

的道

0.84

 verschiedener

0.84

图为

0.83

 latter

0.83

UTIONS

0.83

Activations Density 0.020%