INDEX

Explanations

code structure or context

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

还想

-1.82

ଝ

-1.73

謦

-1.72

 unserer

-1.64

नलोड

-1.63

 rainha

-1.59

 Grüße

-1.58

 poffe

-1.57

衕

-1.55

萑

-1.52

POSITIVE LOGITS

Πηγή

1.59

chtenstein

1.48

Samedi

1.46

Escrito

1.45

Kommentar

1.45

句话

1.45

</h2>

1.40

сної

1.38

Voilà

1.38

 both

1.38

Activations Density 0.004%