INDEX

Explanations

mathematical calculations with exponents

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Thousand

0.47

 thousand

0.43

 previous

0.41

 энергети

0.40

terior

0.40

 dots

0.39

 ponies

0.39

 Alemanha

0.39

譯

0.39

genommen

0.38

POSITIVE LOGITS

Scott

0.43

手

0.42

Miami

0.41

<unused294>

0.41

<u>

0.40

Who

0.40

God

0.39

 oblige

0.39

<unused169>

0.39

Hand

0.38

Activations Density 0.003%