INDEX

Explanations

describes something important or noteworthy

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

 ganchillo

-0.89

zkę

-0.89

 certeza

-0.79

 pierna

-0.76

 cucharadita

-0.76

Better

-0.76

ільки

-0.75

😱

-0.75

rée

-0.73

=[];

-0.73

POSITIVE LOGITS

 worth

4.13

Worth

2.97

 Worth

2.78

值得

2.67

 noteworthy

2.52

 стоит

2.44

 worthy

2.41

worth

2.36

 important

2.36

 note

2.08

Activations Density 0.030%