INDEX

Explanations

references to specific measurements or quantities, particularly those involving ratios, percentages, or degrees

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

 Orrell

-0.69

 gezegd

-0.59

ěst

-0.57

 écrite

-0.56

 spiro

-0.55

зульта

-0.54

uerre

-0.54

 gethan

-0.54

 nervioso

-0.53

 Cæsar

-0.52

POSITIVE LOGITS

of

2.14

OF

1.46

 của

1.35

Of

1.33

of

1.25

 ของ

1.19

.)}

1.18

Of

1.15

ของ

1.15

オブ

1.10

Activations Density 6.524%