INDEX

Explanations

XML tags and structure

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

of

-1.80

for

-1.46

-1.45

НЫЕ

-1.34

If

-1.32

Ál

-1.32

子を

-1.31

 alkoh

-1.30

if

-1.29

 его

-1.29

POSITIVE LOGITS

↵

1.56

 oorsp

1.47

 gebouw

1.45

 zweimal

1.43

 waard

1.41

 obicei

1.39

 cambiamento

1.38

],

1.38

 jähr

1.38

様な

1.37

Activations Density 0.000%