INDEX

Explanations

Alonso and Alfonso variants

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

-2.66

 помогает

-2.55

you

-2.47

 condena

-2.41

淙

-2.38

地的

-2.23

 unſ

-2.20

 repercussions

-2.19

-2.16

的

-2.16

POSITIVE LOGITS

<bos>

2.97

т

2.70

2.48

コト

2.27

wha

2.27

嵎

2.22

できるだけ

2.20

 hermé

2.17

盉

2.13



2.13

Activations Density 0.008%