INDEX

Explanations

words or phrases related to the quality of acting or performance.

performance

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

expandindo

-1.02

HtmlAttribute

-0.88

 '\\;'

-0.88

 שוליים

-0.80

 Italijanski

-0.79

#+#

-0.77

XMLSchema

-0.75

 CreateTagHelper

-0.74

ioutil

-0.72

 dAtA

-0.70

POSITIVE LOGITS

 performance

1.71

 performances

1.46

performance

1.38

 Performance

1.31

Performance

1.30

 PERFORMANCE

1.18

 perform

1.13

 Performances

1.09

PERFORMANCE

1.05

perform

1.04

Activations Density 0.643%