INDEX

Explanations

scientific research papers

thus, 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

 '\\;'

-0.77

terday

-0.77

bibfield

-0.71

bibinfo

-0.70

Vidite

-0.65

存于互联网档案馆

-0.65

InjectAttribute

-0.63

LookAnd

-0.63

 كومونز

-0.62

ăzi

-0.62

POSITIVE LOGITS

 thus

2.80

so

2.50

thus

2.23

Thus

2.19

 Thus

2.09

so

1.91

So

1.80

 así

1.73

 così

1.69

So

1.64

Activations Density 2.650%