INDEX

Explanations

code keywords

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

ერ

-0.69

 bestimmt

-0.69

atical

-0.67

北部

-0.66

 елның

-0.65

았

-0.64

Flan

-0.64

잤

-0.64

 Thông

-0.64

 زیبایی

-0.63

POSITIVE LOGITS

 Biden

0.77

ankind

0.77

Aceite

0.75

extérieur

0.73

 Herausforderung

0.73

 упа

0.71

CONTINUED

0.71

 Bedienung

0.70

Outside

0.70

otella

0.70

Activations Density 0.024%