INDEX

Explanations

outcomes and entities

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

 bisiklet

-1.73

you

-1.70

 burada

-1.64

 preghi

-1.49

↵↵

-1.48

 innych

-1.46

 mutfak

-1.44

または

-1.41

 habia

-1.41

良いです

-1.41

POSITIVE LOGITS

 while

1.57

<td>

1.51

 several

1.42

—

1.37

かわらず

1.36

 ENTRE

1.35

 three

1.34

 ajud

1.30

 negros

1.29

 some

1.28

Activations Density 0.128%