INDEX

Explanations

US states after locations

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setter

-0.85

notated

-0.84

least

-0.84

arent

-0.82

inan

-0.80

uation

-0.80

ties

-0.79

versies

-0.79

もお

-0.79

isan

-0.79

POSITIVE LOGITS

 Illinois

2.11

 Ohio

1.92

 Massachusetts

1.91

TX

1.87

 Pennsylvania

1.84

 California

1.82

 Michigan

1.80

 Wisconsin

1.79

 Missouri

1.74

TX

1.70

Activations Density 0.164%