INDEX

Explanations

that followed by verbs

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

sonaro

-1.63

므

-1.52

薷

-1.49

☆☆☆☆

-1.48

 Moderne

-1.45

 появляется

-1.44

𝑥

-1.44

zei

-1.44

MAXN

-1.42

 kreeg

-1.42

POSITIVE LOGITS

1.85

ünden

1.56

 übri

1.52

颦

1.51

</b>

1.51

and

1.45

 including

1.44

↵↵

1.42

𝙨

1.39

</h4>

1.38

Activations Density 0.074%