INDEX

Explanations

explaining things clearly

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

вање

0.42

 قوي

0.40

 контакта

0.39

系

0.39

Strong

0.39

 zgodnie

0.39

 Distinct

0.39

 použití

0.39

 yönelik

0.38

 Atual

0.38

POSITIVE LOGITS

 manner

0.71

manner

0.64

 nutshell

0.55

 hurry

0.52

 variety

0.50

 multitude

0.46

 manners

0.43

 maniera

0.43

non

0.43

 variedad

0.43

Activations Density 0.066%