INDEX

Explanations

the word "circle", "circles" and "circling"

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

PyExc

-1.13

ngdoc

-0.80

parsedMessage

-0.75

UnusedPrivate

-0.75

 Αν

-0.72

Αν

-0.70

hésite

-0.70

 PropTypes

-0.69

wendi

-0.69

AIT

-0.69

POSITIVE LOGITS

 Circle

1.32

 CIRCLE

1.27

Circle

1.23

 Circles

1.20

 circles

1.18

 circle

1.16

Circles

1.14

CIRCLE

1.12

circles

1.10

circle

1.09

Activations Density 0.012%