INDEX

Explanations

mentions of restaurants and dining

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

 getLogin

-0.73

 Akin

-0.71

.*")]

-0.66

jeune

-0.66

 Mauer

-0.66

 mData

-0.66

 Gier

-0.66

vdash

-0.65

président

-0.65

Folge

-0.65

POSITIVE LOGITS

 restaurants

1.18

 restaurant

1.04

 Restaurants

1.04

 Restaurant

1.01

Restaurants

0.96

restaurants

0.94

Restaurant

0.93

 RESTAURANT

0.90

WriteLiteral

0.87

restaurant

0.83

Activations Density 0.005%