INDEX

Explanations

producer followed by name

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ЦИ

-0.84

cloudfront

-0.77

("/",

-0.77

ⲣ

-0.77

𝑬

-0.77

verson

-0.75

☾

-0.75

 служ

-0.71

翰

-0.71

riko

-0.71

POSITIVE LOGITS

 producer

3.34

producer

2.89

 producers

2.88

 Producer

2.66

Producer

2.53

Producers

2.39

 PRODUC

2.39

 producing

2.36

 Producers

2.34

 produced

2.28

Activations Density 0.073%