INDEX

Explanations

introduces details or comparisons

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

بندی

-1.23

تفسير

-1.21

不是

-1.20

one

-1.16

私の

-1.14

<bos>

-1.14

توضیحات

-1.14

معرفی

-1.13

 grup

-1.13

其中

-1.11

POSITIVE LOGITS

つづく

1.27

眼底

1.27

はこんな感じ

1.26

えっ

1.25

 being

1.25

あー

1.24

を作って

1.23

来週

1.21

 vertrouwen

1.21

めちゃ

1.20

Activations Density 0.101%