INDEX

Explanations

numeric values

Unclear

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

<bos>

-0.70

+#+#

-0.63

 betweenstory

-0.57

AndEndTag

-0.55

ArgsConstructor

-0.55

CppMethod

-0.54

AddTagHelper

-0.54

 Italijanski

-0.54

 Alcott

-0.54

 OFDb

-0.53

POSITIVE LOGITS

putExtra

0.36

iodía

0.36

bbi

0.36

ftant

0.35

 dira

0.34

erf

0.33

ως

0.33

UnitOfWork

0.33

辈子

0.32

erweise

0.32

Activations Density 2.723%