INDEX

Explanations

acts

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.79

 consultato

-0.67

stalt

-0.64

Captor

-0.63

Lähteet

-0.63



-0.63

PhysRev

-0.62

 Juga

-0.61

fortawesome

-0.59

 obstante

-0.59

POSITIVE LOGITS

0.59

 henne

0.47

am

0.45

elemento

0.45

eden

0.45

뉴

0.44

semibold

0.41

gt

0.41

 мол

0.41

tal

0.40

Activations Density 0.039%