INDEX

Explanations

how something is done

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

the

0.33

 muốn

0.29

 Want

0.29

chc

0.29

 хочу

0.28

 เพื่อ

0.28

 yapmak

0.28

 để

0.27

ல்

0.27

 hacer

0.27

POSITIVE LOGITS

 dint

0.29

 poprzez

0.28

 કરીને

0.26

 realistically

0.25

izando

0.25

 nöt

0.25

 اولا

0.25

埴

0.24

éc

0.24

íd

0.24

Activations Density 0.014%