INDEX

Explanations

competitive programming pragmas

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

 平成

-0.90

nés

-0.80

 ayat

-0.79

Revenir

-0.77

下さい

-0.75

וֹת

-0.73

 دارند

-0.73

博物館

-0.71

šnje

-0.71

 SPAN

-0.71

POSITIVE LOGITS

Competitive

1.16

 Competitive

1.15

competitive

1.12

freopen

0.99

蒻

0.97

cin

0.95

 Contest

0.95

 competitive

0.94

contest

0.92

 sieve

0.91

Activations Density 0.069%