INDEX

Explanations

technical/formal records

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.59

+#+#

-0.57

OwnProperty

-0.53

 виправивши

-0.50

apimachinery

-0.49

Obrázky

-0.48

таратура

-0.48

ldorf

-0.42

ukov

-0.42

يكب

-0.41

POSITIVE LOGITS

pat

0.62

reter

0.60

DeleteBehavior

0.60

ogast

0.59

Pat

0.59

Pat

0.58

พาะ

0.55

mogat

0.55

 consultato

0.54

obel

0.54

Activations Density 0.003%