INDEX

Explanations

Scientific, multilingual texts

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 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

 كومونز

-0.79

 surla

-0.69

XmlAccessType

-0.67

 betweenstory

-0.67

исленность

-0.60

wpi

-0.60

 ویکی‌پدیا

-0.59

MLLoader

-0.57

AddHtmlAttribute

-0.56

MessageOf

-0.54

POSITIVE LOGITS

NOPQRST

0.54

ArrowToggle

0.52

nadas

0.49

 Tark

0.46

itan

0.46

ungszeit

0.46

rijven

0.45

ówek

0.45

neh

0.44

 사이

0.43

Activations Density 0.005%