INDEX

Explanations

completion

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 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

 finish

-1.33

 finished

-1.18

 enjoy

-1.16

finish

-1.13

 Finished

-1.13

finished

-1.05

 celebrate

-1.01

 Finish

-1.00

Finished

-0.99

 harvest

-0.96

POSITIVE LOGITS

 volunteering

0.64

SharedCtor

0.64

 betweenstory

0.62

 հղումներ

0.61

LabelTagHelper

0.59

parsedMessage

0.58

 mediana

0.55

ResponseWriter

0.55

 OMIT

0.54

featureID

0.53

Activations Density 0.571%