INDEX

Explanations

foreign words and sounds

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

<bos>

-1.52

 five

-1.30

などが

-1.30

方針

-1.30

 three

-1.28

そのため

-1.28

つまり

-1.27

 four

-1.24

 because

-1.18

意見

-1.17

POSITIVE LOGITS

corrhi

1.41

為に

1.28

あー

1.27

づけ

1.25

 км

1.24

うわ

1.22

のですか

1.19

 hué

1.17

えっ

1.16

 porc

1.16

Activations Density 0.011%