INDEX

Explanations

the word "near."

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

No Comments

Negative Logits

Near

-1.16

 Near

-1.14

near

-1.08

 near

-1.06

 NEAR

-0.82

NEAR

-0.76

近

-0.55

pot

-0.53

 nigh

-0.53

Искәрмәләр

-0.50

POSITIVE LOGITS

<bos>

0.73

 CHtml

0.65

 itſelf

0.64

 betweenstory

0.59

 børn

0.57

 isKindOfClass

0.56

Tembelea

0.56

MENAFN

0.56

 AspNetCore

0.56

 Walkover

0.56

Activations Density 0.720%