INDEX

Explanations

box and following words

box of

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

Finding

0.54

0.49

fabric

0.49

Chia

0.48

fers

0.47

CHP

0.47

0.46

Cups

0.46

↵

0.45

POSITIVE LOGITS

box

1.57

Box

1.51

 बॉक्स

1.44

 Boxes

1.41

 boxes

1.37

BOX

1.36

 короб

1.31

Box

1.26

箱

1.23

 باکس

1.21

Activations Density 0.048%