INDEX

Explanations

legal arguments and constructions

New England 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

 interpret

-2.02

 INTERPRET

-1.98

 interpreting

-1.97

 Interpretation

-1.96

 interpretation

-1.93

 Interpret

-1.89

 Interpre

-1.88

Interpretation

-1.86

Interpret

-1.86

 interpretations

-1.84

POSITIVE LOGITS

 Boston

1.45

 Massachusetts

1.41

Boston

1.40

Massachusetts

1.38

 Connecticut

1.30

Connecticut

1.26

 BOSTON

1.23

 boston

1.20

BOSTON

1.10

 MASSACHUSETTS

1.09

Activations Density 3.346%