INDEX

Explanations

positive adjectives, especially the word "great."

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

strophy

-0.85

‚¬

-0.79

createCell

-0.79

aarrggbb

-0.75

 cré

-0.71

زیک

-0.70

ภัณฑ์

-0.68

indrome

-0.67

 Create

-0.67

createFrom

-0.66

POSITIVE LOGITS

 quoque

0.59

Geb

0.59

RegressionTest

0.59

 Armas

0.58

 Stepan

0.58

 Radu

0.57

 trots

0.57

Wyd

0.57

YourGuide

0.56

istert

0.56

Activations Density 0.013%