INDEX

Explanations

numbers, letters, and words

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

 kilomet

-1.51

قامت

-1.36

 millioner

-1.34

گاهی

-1.30

จาก

-1.30

שלום

-1.26

אם

-1.26

besondere

-1.25

ถ้า

-1.25

を選択します

-1.20

POSITIVE LOGITS

−/−

1.44

1.40

也太

1.30

aning

1.25

 éstas

1.24

そういった

1.23

为什么会

1.22

1.21

好像是

1.21

to

1.21

Activations Density 0.003%