INDEX

Explanations

references to making things up or creating false information

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

$_"

-0.83

writeFieldEnd

-0.79

AsUp

-0.76

writeField

-0.74

setVerticalGroup

-0.73

 contextLoads

-0.72

SEGUIR

-0.72

InvalidProtocol

-0.71

 auroit

-0.71

 avoient

-0.70

POSITIVE LOGITS

 make

0.60

<bos>

0.57

rewsbury

0.52

make

0.51

 made

0.50

made

0.48

不如

0.46

новниш

0.46

 Schweiz

0.45

zación

0.45

Activations Density 0.479%