INDEX

Explanations

Duolingo or with code

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

 불구하고

1.47

patial

1.26

 त्यस

1.25

 அதனால்

1.21

 quello

1.21

 înce

1.16

 Veľ

1.16

 nello

1.16

 większość

1.15

 atteindre

1.15

POSITIVE LOGITS

ar

1.52

ה

1.44

त

1.38

est

1.36

1.27

 gentamicin

1.26

𝗺

1.24

्याम

1.22

एन

1.19

쪽

1.18

Activations Density 0.011%