INDEX

Explanations

programming 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

 یا

-2.59

).

-2.36

 Anſ

-2.22

 ſou

-2.14

 или

-2.13

 humeur

-2.09

 עם

-2.06

 ſch

-2.02

没有

-1.93

鐧

-1.93

POSITIVE LOGITS

2.78

</u>

2.55

2.31

↵

2.11

 koruma

2.08

you

2.03

 wydaje

1.91

ようですが

1.91

</code>

1.90

 Auffassung

1.90

Activations Density 0.001%