INDEX

Explanations

language descriptions

built them or drives so

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 detox

0.26

 curation

0.25

%\

0.25

])*

0.25

 cyanide

0.25

 Kindern

0.24

 reduces

0.24

)$

0.24

 retention

0.24

 retrieval

0.24

POSITIVE LOGITS

ymmetrical

0.30

 אר

0.28

 различные

0.28

一般的な

0.27

trendy

0.27

 стаття

0.27

disco

0.26

 основные

0.25

outro

0.25

typen

0.25

Activations Density 0.179%