INDEX

Explanations

regular expression syntax

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.89

 Quill

-0.77

Yin

-0.77

Hochspringen

-0.77

 Marqu

-0.76

 MonoBehaviour

-0.75

 Augu

-0.75

 yolks

-0.74

AsUp

-0.74

 Wynne

-0.73

POSITIVE LOGITS

.*

0.93

ة

0.73

 anyone

0.69

ing

0.68

Teb

0.68

yah

0.66

 FormsModule

0.66

(.*

0.65

ią

0.64

 bere

0.63

Activations Density 0.008%