INDEX

Explanations

numbers and punctuation

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

 ثم

-0.75

can

-0.73

 verme

-0.69

rdida

-0.67

小的

-0.66

 Bremer

-0.66

roskop

-0.66

JEE

-0.66

 Kush

-0.65

dostęp

-0.65

POSITIVE LOGITS

剎

0.87

ímos

0.80

Fø

0.79

 namanya

0.79

 bình

0.78

 renang

0.78

 オイル

0.76

Ikke

0.73

 fantástico

0.72

 верно

0.72

Activations Density 0.040%