INDEX

Explanations

common phrase starters

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

 very

-0.95

kilde

-0.94

 perhaps

-0.89

 burgeoning

-0.88

 quaint

-0.83

 agus

-0.83

 great

-0.83

lateinit

-0.82

 vanwege

-0.82

POSITIVE LOGITS

arbeiten

1.06

 griechischen

1.03

>(),

1.02

 Dlatego

1.00

 internetu

1.00

 jednom

1.00

 פאר

1.00

 ktore

0.99

 jste

0.98

considered

0.97

Activations Density 0.006%