INDEX

Explanations

names

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.82

مصادر

-0.63

ⓧ

-0.46

-0.42

पया

-0.40

WithIOException

-0.38

 Krakowie

-0.38

lorum

-0.38

Wein

-0.38

 contes

-0.37

POSITIVE LOGITS

 Fittings

0.64

AddAttribute

0.63

 Cloning

0.59

goat

0.58

 ConstraintSet

0.57

writeField

0.57

 Birch

0.57

 Biomedical

0.57

jspb

0.56

colar

0.55

Activations Density 0.025%