INDEX

Explanations

list items or categories

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

 yeri

0.41

ذور

0.40

 دھو

0.39

Claudia

0.39

τ

0.39

𝑵

0.38

γ

0.38

ដ

0.38

Ն

0.37

Seeds

0.37

POSITIVE LOGITS

 Сол

0.39

}_{-

0.39

 นอกจาก

0.38

 Bedarf

0.38

 гори

0.36

以便

0.36

zak

0.36

Mhm

0.36

 BECAUSE

0.36

避

0.35

Activations Density 0.007%