INDEX

Explanations

URLs and web addresses

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

 estis

-1.11

if

-1.08

(!__

-1.05

리가

-1.02

end

-1.02

utivos

-0.98

 These

-0.97

 accordance

-0.96

欲しい

-0.95

utsches

-0.94

POSITIVE LOGITS

 Игорь

1.30

 portátiles

1.26

 Сергей

1.17

čo

1.14

所示

1.09

誇

1.09

違い

1.08

 وليس

1.07

 tornillos

1.07

 brilho

1.06

Activations Density 0.001%