INDEX

Explanations

code block delimiters

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

تیجه

-1.84

ٴ

-1.84

罨

-1.74

镲

-1.70

?”

-1.68

 енер

-1.68

 gustado

-1.65

捽

-1.64

”:

-1.64

:");

-1.61

POSITIVE LOGITS

1.69

…

1.68

生まれ

1.56

 myriad

1.51

 realizando

1.49

 dando

1.43

 ولم

1.42

 thre

1.41

 considerando

1.40

乜

1.39

Activations Density 0.003%