INDEX

Explanations

coordinates and dimensions

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

 however

-1.31

 però

-1.27

 však

-1.25

 fevere

-1.23

 チェック

-1.22

 whom

-1.20

 cinqu

-1.19

 seront

-1.18

ített

-1.17

 поможет

-1.17

POSITIVE LOGITS

one

1.26

 llena

1.22

 only

1.22

 नि

1.21

 Bardzo

1.16

my

1.13

 detener

1.12

=}

1.10

 ragazzo

1.10

 first

1.09

Activations Density 0.100%