INDEX

Explanations

comma

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

 ModelExpression

-0.85

 itſelf

-0.72

出版年

-0.72

 Chwiliwch

-0.71

 nahilalakip

-0.71

setVerticalGroup

-0.67

 noDo

-0.63

 NavController

-0.60

lloworld

-0.59

ագրություններ

-0.59

POSITIVE LOGITS

ustes

0.60

ENTE

0.56

Vic

0.52

 adverse

0.51

 respecter

0.50

rogenic

0.48

 Currie

0.47

 truth

0.47

ivasan

0.47

 weep

0.46

Activations Density 0.033%