INDEX

Explanations

matically

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Aires

-0.46

se

-0.46

tised

-0.45

 known

-0.44

cripts

-0.44

 marked

-0.44

seins

-0.43

sements

-0.42

Poland

-0.41

so

-0.41

POSITIVE LOGITS

0.77

 '\\;'

0.72

UnsafeEnabled

0.72

FieldBuilder

0.71

WriteBarrier

0.71

NameInMap

0.69

 Benth

0.67

 Theſe

0.66

webElementXpaths

0.66

HtmlAttribute

0.65

Activations Density 0.059%