INDEX

Explanations

some followed by a word

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ському

1.73

 был

1.72

शिला

1.68

 був

1.57

冕

1.56

 расположение

1.55

 tidak

1.55

uelto

1.55

 menurut

1.54

ítě

1.54

POSITIVE LOGITS

`;

1.86

things

1.85

exceptions

1.76

$("

1.73

ेक

1.65

<$

1.63

memberNameLink

1.62

$('

1.57

 awfully

1.56

개의

1.56

Activations Density 3.144%