INDEX

Explanations

do

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

 auto

-0.51

 fall

-0.46

dr

-0.45

car

-0.44

car

-0.43

dw

-0.42

dw

-0.41

Dw

-0.41

 need

-0.40

POSITIVE LOGITS

ArgsConstructor

0.75

MessageTagHelper

0.75

titleMargin

0.74

TagMode

0.73

modb

0.73

ftagPool

0.73

toMatchSnapshot

0.71

 насељу

0.70

 defStyle

0.70

 MainAxisSize

0.70

Activations Density 0.683%