INDEX

Explanations

quoted strings or code snippets

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

 Produk

-0.97

ねぇ

-0.96

襁

-0.96

 pudieran

-0.93

🤤

-0.91

likat

-0.88

mäs

-0.87

zbęd

-0.86

 karna

-0.85

ühnen

-0.85

POSITIVE LOGITS

 this

2.92

 это

1.87

 هذا

1.63

 Это

1.54

 This

1.52

 hello

1.45

 THIS

1.34

 Hello

1.34

This

1.32

 some

1.31

Activations Density 0.112%