INDEX

Explanations

a mix of location names, political words, and parts of code

cities

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

 InputDecoration

-0.50

BeforeClass

-0.48

 EINVAL

-0.46

unan

-0.45

ScopeManager

-0.44

tauan

-0.44

quiel

-0.43

 fasci

-0.43

CodeAnalysis

-0.42

HasKey

-0.42

POSITIVE LOGITS

 Nairobi

0.91

 London

0.88

 Dublin

0.88

 Sydney

0.87

 Toronto

0.83

 Chicago

0.83

 Bucharest

0.82

 Jakarta

0.82

 Manila

0.82

 Atlanta

0.81

Activations Density 3.179%