INDEX

Explanations

code structure identifiers

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

 that

-1.55

as

-1.41

著名

-1.22

你是不是

-1.21

孑

-1.19

 feststellen

-1.11

 since

-1.11

 whether

-1.09

of

-1.08

我们是

-1.07

POSITIVE LOGITS

 lakini

1.48

细腻

1.43

they

1.40

ACIÓN

1.40

WARDS

1.30

"")

1.28

कृति

1.25

ZIE

1.24

hmä

1.23

ullah

1.21

Activations Density 0.093%