INDEX

Explanations

proper names, especially in contexts that suggest they are people affiliated with an organization

names in technical texts

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

 sauvages

-0.51

IsMutable

-0.50

 définiti

-0.50

 scolaires

-0.48

 femininas

-0.48

 humains

-0.48

 mesmas

-0.48

 Taktlose

-0.48

 propOrder

-0.47

 Menschheit

-0.46

POSITIVE LOGITS

ía

0.46

0.45

era

0.43

}]

0.43

án

0.42

ô

0.42

î

0.42

Eig

0.42

à

0.42

ám

0.41

Activations Density 5.575%