INDEX

Explanations

decorators and special keywords

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

enment

-1.65

-1.55

 salari

-1.55

istics

-1.55

Ꮀ

-1.54

数が

-1.52

 permita

-1.51

 oiseau

-1.50

мови

-1.49

aneity

-1.48

POSITIVE LOGITS

of

1.66

 this

1.55

 erklär

1.53

↵

1.50

While

1.49

文化的

1.46

Through

1.46

なく

1.42

at

1.41

for

1.39

Activations Density 0.007%