INDEX

Explanations

references to licensing and legal compliance related to software or data use

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

 conform

-1.48

 conforms

-1.44

 adhere

-1.34

 adheres

-1.20

 comply

-1.19

 conforming

-1.16

 adhered

-1.13

 adhering

-1.11

 abide

-1.05

 complies

-1.03

POSITIVE LOGITS

 Compliance

1.06

 compliance

1.05

 kasarigan

0.96

Compliance

0.90

compliance

0.87

NameInMap

0.66

SerializeField

0.61

 esper

0.59

 jScrollPane

0.59

"}";

0.56

Activations Density 0.002%