INDEX

Explanations

Trust

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

trust

-0.77

 trust

-0.73

 Trust

-0.72

Trust

-0.70

 trusts

-0.57

TRUST

-0.56

 TRUST

-0.56

 Trusts

-0.55

 humeur

-0.53

 confiance

-0.53

POSITIVE LOGITS

ConstraintMaker

1.05

StoryboardSegue

1.03

 Pingback

0.77

SequentialGroup

0.77

Искәрмәләр

0.71

AnimationsModule

0.69

WithEmail

0.69

Datuak

0.68

 Erişim

0.66

 ویکی‌پدیای

0.65

Activations Density 0.039%