INDEX

Explanations

introducing a thought or idea

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

 with

-2.05

 using

-1.92

 removing

-1.59

 fifteen

-1.58

any

-1.55

 enhances

-1.53

 eleven

-1.51

one

-1.50

 reducing

-1.50

 from

-1.49

POSITIVE LOGITS

౭

1.70

 ส์

1.58

 magnific

1.56

一闪

1.46

WIL

1.45

 semelh

1.43

niti

1.43

trying

1.43

 suave

1.41

Activations Density 0.057%