INDEX

Explanations

programming and scientific contexts

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

 have

-1.37

 their

-1.31

by

-1.25

to

-1.25

 before

-1.22

 when

-1.20

 last

-1.20

for

-1.16

 because

-1.16

 zelfs

-1.10

POSITIVE LOGITS

 również

1.36

quirer

1.16

 также

1.15

嗚

1.13

 också

1.13

 também

1.13

werben

1.10

Сер

1.07

Зага

1.06

 faisaient

1.06

Activations Density 0.000%