INDEX

Explanations

programming code and questions

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

 from

-1.65

the

-1.53

 your

-1.52

 helpt

-1.41

dáms

-1.41

 vierge

-1.34

ܜ

-1.30

濶

-1.27

Ꮵ

-1.27

さっき

-1.27

POSITIVE LOGITS

を

1.42

can

1.36

 naudoti

1.33

 användas

1.28

 else

1.26

↵↵

1.26

1.25

이

1.24

这个

1.23

Activations Density 0.011%