INDEX

Explanations

various symbols and technical terms

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

 burgeoning

-2.31

 longstanding

-2.20

 sizeable

-2.20

 Even

-2.19

ではでは

-2.17

 because

-2.16

 facilitating

-2.16

 cleverly

-2.14

 substantial

-2.13

ちなみに

-2.13

POSITIVE LOGITS



2.80



2.58

 somewhat

2.55

 unbelievably

2.44

 overly

2.44

 delightfully

2.44

 unending

2.44

 largely

2.38

 decidedly

2.36

 exceedingly

2.34

Activations Density 0.001%