INDEX

Explanations

references to boilers and their associated components or activities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 oven

-0.93

 Oven

-0.84

Oven

-0.76

oven

-0.72

 kitchen

-0.68

 Kitchen

-0.67

 baking

-0.62

Kitchen

-0.61

Genuine

-0.59

 KITCHEN

-0.57

POSITIVE LOGITS

 cook

1.91

cook

0.98

 cooks

0.94

 boiler

0.72

 Allociné

0.60

boiler

0.60

 ekor

0.59

 boilers

0.57

 mieli

0.57

 Américas

0.56

Activations Density 0.006%

No Known Activations