INDEX

Explanations

roleplay and questions

language that directly addresses the reader or refers to the speaker (second- and first-person pronouns in conversational context).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

阅读

0.41

 obscure

0.40

疑问

0.40

0.39

 Curious

0.38

 mumbled

0.38

 それ

0.38

 Hogwarts

0.38

 Question

0.38

 Studying

0.38

POSITIVE LOGITS

 selaku

0.59

zelf

0.57

 sendiri

0.51

ون

0.45

رسٹ

0.41

زش

0.41

ليس

0.40

لس

0.40

 ruolo

0.39

зир

0.39

Activations Density 0.215%