INDEX

Explanations

gg followed by a word

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

It

-2.89

 them

-2.59

er

-2.55

 którzy

-2.39

<em>

-2.38

的一些

-2.34

 launches

-2.31

附属

-2.30

 verschill

-2.28

 achieving

-2.25

POSITIVE LOGITS

2.98

鬭

2.89

ным

2.88

꯳

2.69

gg

2.58

笮

2.53

筇

2.41

都想

2.33

 стал

2.31

まき

2.30

Activations Density 0.008%