INDEX

Explanations

code structure delimiters

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

 başlad

-1.41

もありました

-1.31

そして

-1.30

 consé

-1.29

しかも

-1.28

 requête

-1.27

 rağmen

-1.25

 başlay

-1.25

')),

-1.24

"):

-1.24

POSITIVE LOGITS

2.45

1.90

了很多

1.42

1.32

 ovviamente

1.30

 zamiast

1.30

</strong>

1.29

1.25

1.23

Activations Density 0.010%