INDEX

Explanations

So

the start of statements involving the word "so."

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

UnusedPrivate

-0.64

TagMode

-0.61

BagConstraints

-0.60

XmlRootElement

-0.58

 мәкалә

-0.57

UrlResolution

-0.56

PreferredItem

-0.55

Склад

-0.55

 OnInit

-0.54

utnik

-0.54

POSITIVE LOGITS

 gainera

0.50

unità

0.42

oa̍t

0.41

เภ

0.41

 clou

0.41

en

0.41

+#+#

0.41

령

0.40

ETRY

0.40

 ͜ʖ

0.40

Activations Density 0.890%