INDEX

Explanations

positive and negative ways

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

Ủ

0.42

 produkt

0.40

 πλη

0.40

عام

0.39

 Aufenthalt

0.39

 अधिकांश

0.39

RR

0.39

 zahlen

0.39

 NSUInteger

0.39

فیلم

0.39

POSITIVE LOGITS

 ways

1.11

 manner

1.08

 manière

1.05

方式

1.04

way

1.02

 maniera

1.01

 manera

0.99

 şekilde

0.94

 façon

0.93

 maneira

0.91

Activations Density 0.115%