INDEX

Explanations

lists of diverse items

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

 aggravate

0.48

 pollute

0.47

 contaminate

0.43

 generalize

0.41

 hypothesize

0.41

lande

0.39

agwa

0.39

 useless

0.39

生素

0.38

 похоже

0.38

POSITIVE LOGITS

候補

0.45

 enunciado

0.45

 spinster

0.39

第二百

0.38

("'

0.38

候选

0.37

misc

0.37

Ⅼ

0.37

ponsors

0.37

瓠

0.37

Activations Density 0.001%