INDEX

Explanations

complex concepts and reasoning

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

 всем

1.53

 всеми

1.31

‍♀️

1.27

 बदनाम

1.22

好处

1.21

‍♂️

1.14

ժ

1.13

ন

1.11

ۥ

1.09

 worse

1.09

POSITIVE LOGITS

 interplay

1.76

я

1.62

 conjugate

1.57

ة

1.57

다

1.53

es

1.51

्ठा

1.48

 mult

1.45

 nuanced

1.42

 interwoven

1.39

Activations Density 0.123%