INDEX

Explanations

`open` followed by `parser`

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

to

-1.40

for

-1.20

</b>

-1.20

 sogar

-1.16

Karakter

-1.13

olução

-1.13

랐

-1.09

人を

-1.09

后来

-1.08

不同

-1.07

POSITIVE LOGITS

 nhưng

1.31

 meinte

1.30

\'

1.23

1.20

ільки

1.18

 quienes

1.17

қы

1.17

 sonre

1.16

%;

1.15

 cojín

1.15

Activations Density 0.085%