INDEX

Explanations

code snippets and inline text

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

 Encyclop

0.21

 ogrom

0.21

benhav

0.21

Grilled

0.21

茘

0.21

१०

0.20

Incl

0.20

 acht

0.19

 Igreja

0.19

POSITIVE LOGITS

 values

0.24

<unused2199>

0.24

 ethnicity

0.23

 socials

0.23

_)

0.22

 output

0.22

 taxes

0.22

 input

0.22

गेट

0.22

 varsa

0.22

Activations Density 0.563%