INDEX

Explanations

numbers and punctuation

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

our

-2.03

-1.70

มากๆ

-1.63

 أخرى

-1.51

чните

-1.45

文化的

-1.41

 them

-1.38

an

-1.38

第六

-1.38

 your

-1.37

POSITIVE LOGITS

从来没有

1.59

分辨

1.47

还不是

1.41

察觉

1.36

1.33

尽量

1.31

 MINUTE

1.30

 provocando

1.29

 dangers

1.28

1.27

Activations Density 0.010%