INDEX

Explanations

code module names

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

if

-1.39

盉

-1.23

 inexperienced

-1.23

没问题

-1.23

 изменение

-1.22

ranton

-1.20

ฯ

-1.20

 interieur

-1.20

 positioned

-1.19

 решил

-1.18

POSITIVE LOGITS

but

2.05

and

1.64

 saveurs

1.57

 Provinz

1.37

 météoro

1.36

 mémor

1.34

 These

1.33

 նաև

1.30

1.27

 soixante

1.27

Activations Density 0.035%