INDEX

Explanations

numbers and punctuation

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

We

0.27

 benutzen

0.25

 Haha

0.25

 আমি

0.24

 disagreed

0.23

 VERY

0.23

 haha

0.22

 violently

0.22

 Politics

0.22

 veldig

0.22

POSITIVE LOGITS

 столь

0.24

تباين

0.23

erequisite

0.23

可通过

0.22

 fosters

0.22

有助于

0.22

ѐ

0.22

Согласно

0.21

 किंतु

0.21

 decorative

0.20

Activations Density 0.000%