INDEX

Explanations

distributed

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

transQ

-0.64

 iprot

-0.60

تقاوى

-0.55

BufferException

-0.54

 defaultstate

-0.53

 endwhile

-0.53

ConstraintMaker

-0.52

Wii

-0.51

DataAnnotations

-0.50

 CUDA

-0.50

POSITIVE LOGITS

ization

0.68

ised

0.61

ized

0.61

izable

0.56

isation

0.56

lative

0.54

tably

0.53

 &___

0.53

cillo

0.53

izes

0.51

Activations Density 0.146%