INDEX

Explanations

the word "tour"

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

 propOrder

-0.81

zwischen

-0.78

tedy

-0.75

rrggbb

-0.66

География

-0.66

hesda

-0.66

ITERIA

-0.65

 TEMPO

-0.64

Rp

-0.63

//};

-0.62

POSITIVE LOGITS

 tours

1.70

 Tour

1.68

 Tours

1.65

 tour

1.60

Tour

1.60

tour

1.54

 TOUR

1.52

Tours

1.52

tours

1.42

TOUR

1.39

Activations Density 0.005%