INDEX

Explanations

the followed by descriptive word

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

あるいは

0.28

 distinction

0.25

transformation

0.24

 existence

0.24

personen

0.23

로부터

0.23

および

0.23

 अथवा

0.23

erdapat

0.23

 focus

0.23

POSITIVE LOGITS

 kinda

0.34

 crappy

0.34

 weird

0.32

 scary

0.31

 comunes

0.30

 originals

0.30

 sneaky

0.29

 usual

0.29

 wacky

0.29

 sketchy

0.29

Activations Density 0.062%