INDEX

Explanations

code constructs and keywords

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

 снова

-1.71

 ранее

-1.42

 again

-1.32

 последний

-1.30

ἵ

-1.27

avoit

-1.27

 غذایی

-1.27

 znovu

-1.27

 rimane

-1.26

 opět

-1.26

POSITIVE LOGITS

靭

1.52

靱

1.33

此事

1.29

啻

1.29

 Богу

1.28

 verwijzen

1.27

éton

1.23

emate

1.22

 такі

1.22

онка

1.21

Activations Density 0.045%