INDEX

Explanations

various aspects of research papers and formatted numerical data

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

No Comments

Negative Logits

 three

-0.83

 Three

-0.81

 trio

-0.78

 الثلاث

-0.73

Three

-0.72

three

-0.70

 tres

-0.70

 trois

-0.70

三

-0.68

 três

-0.66

POSITIVE LOGITS

ScopeManager

0.53

DoubleQuotes

0.52

 transfieras

0.51

homonymie

0.48

ỏi

0.48

τεύ

0.48

 članak

0.46

systemctl

0.46

oaks

0.46

 blessure

0.45

Activations Density 1.506%