INDEX

Explanations

"To" followed by verbs indicating purpose

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

to

-2.03

熒

-1.56

but

-1.55

去

-1.54

obut

-1.49

/>";

-1.41

 обладает

-1.39

१

-1.38

داً

-1.37

 because

-1.35

POSITIVE LOGITS

he

1.91

ANIEL

1.74

揄

1.58

ers

1.56

of

1.53

 help

1.52

 seiner

1.52

üsseldorf

1.50

upaten

1.48

揍

1.48

Activations Density 0.044%