INDEX

Explanations

numbers in code contexts

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

 меню

-0.93

and

-0.88

readFileSync

-0.87

teli

-0.83

şak

-0.80

 Markers

-0.79

عکس

-0.78

Rad

-0.78

死ぬ

-0.77

Ahora

-0.76

POSITIVE LOGITS

<bos>

0.98

薔薇

0.90

ponible

0.87

但却

0.86

って思

0.86

λίου

0.84

Ventas

0.84

違って

0.83

васто

0.82

延長

0.81

Activations Density 0.029%