INDEX

Explanations

with

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

 trivial

-0.51

ورش

-0.45

 awak

-0.44

 wave

-0.44

copal

-0.43

 Pernambuco

-0.43

 (€

-0.42

dre

-0.42

DRA

-0.41

antur

-0.41

POSITIVE LOGITS

rungsseite

0.95

Билгалдахарш

0.80

ValueStyle

0.73

abestanden

0.73

aarrggbb

0.72

 tartalomajánló

0.71

 Мексичка

0.70

 estekak

0.69

 تانيه

0.69

ollectionView

0.67

Activations Density 0.001%