INDEX

Explanations

localization data formats

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

removeAttr

-0.69

窗

-0.68

okko

-0.67

 obter

-0.67

 Theologie

-0.66

 damas

-0.65

 生日

-0.65

 maș

-0.65

 know

-0.63

できれば

-0.62

POSITIVE LOGITS

Wallis

0.91

ulateur

0.86

 region

0.84

עת

0.82

Transforms

0.81

oran

0.79

 Erickson

0.78

 vám

0.77

 denne

0.76

 propOrder

0.75

Activations Density 0.026%