INDEX

Explanations

called encryption keys

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

くちゃ

-1.45

 иной

-1.41

 écouter

-1.30

 rêver

-1.29

 относительно

-1.27

 olacaktır

-1.27

 courir

-1.23

Одна

-1.20

 другое

-1.18

 недавно

-1.17

POSITIVE LOGITS

 because

2.48

for

2.25

 when

2.08

 یا

1.79

or

1.73

by

1.67

 unless

1.63

 until

1.59

if

1.56

 eftersom

1.45

Activations Density 0.280%