INDEX

Explanations

question or list items

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

in

-1.73

on

-1.47

at

-1.45

so

-1.41

 should

-1.34

 because

-1.34

as

-1.30

 using

-1.30

 both

-1.28

 often

-1.27

POSITIVE LOGITS

 foglie

1.25

吃

1.20

 garantir

1.17

rô

1.16

Eſ

1.16

 Dinas

1.15

ſelf

1.14

ዣ

1.13

yarnpkg

1.13

WHERE

1.13

Activations Density 0.016%