INDEX

Explanations

mapping and grouping data structures

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

我們

-1.63

ztes

-1.60

 Schwierigkeiten

-1.57

 новая

-1.52

 längere

-1.50

oucí

-1.49

铙

-1.46

ኗ

-1.42

踉

-1.42

 hoher

-1.40

POSITIVE LOGITS

of

2.17

 including

1.67

—

1.60

 vincit

1.59

—

1.55

not

1.54

 trough

1.49

 much

1.44

at

1.41

 here

1.37

Activations Density 0.023%