INDEX

Explanations

to followed by a verb

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

慙

-1.73

敺

-1.73

が上が

-1.71

 avenir

-1.63

 estadounid

-1.60

 saveurs

-1.59

 pérd

-1.57

鯔

-1.57

 AVENUE

-1.55

 goûts

-1.55

POSITIVE LOGITS

1.83

."

1.57

);

1.43

 ένας

1.42

.'

1.39

":[{

1.38

In

1.37

 think

1.36

”

1.35

 resemble

1.34

Activations Density 0.009%