INDEX

Explanations

examples or specific listings

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

 Appreciation

0.21

 incompetence

0.20

!]

0.20

 nowDate

0.20

 अदर

0.20

یثیت

0.20

 physicality

0.20

认真

0.19

 innego

0.19

 zmian

0.19

POSITIVE LOGITS

 those

0.30

 ones

0.28

 quelli

0.27

 bernama

0.24

՝

0.23

一つ

0.23

examples

0.23

例えば

0.23

 주로

0.23

 favorites

0.22

Activations Density 0.601%