INDEX

Explanations

statements about one's attitude towards a situation or subject

say "cause/effect words"

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

 they

-0.88

we

-0.70

Because

-0.69

because

-0.63

 они

-0.63

 StatefulWidget

-0.62

 Because

-0.62

 there

-0.61

 она

-0.58

he

-0.58

POSITIVE LOGITS

as

1.07

 как

0.63

 AssemblyProduct

0.61

asa

0.56

 Himo

0.54

 як

0.52

selaer

0.52

Rüyada

0.50

ofollow

0.50

 ainsi

0.50

Activations Density 0.584%