INDEX

Explanations

the word 'nearby'

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

UnknownFieldSet

-0.59

 direct

-0.52

house

-0.52

direct

-0.51

apatan

-0.51

House

-0.50

 Hoss

-0.49

fromLTRB

-0.48

 betul

-0.48

 Фи

-0.47

POSITIVE LOGITS

Nearby

0.99

nearby

0.96

 Nearby

0.94

 nearby

0.84

 /\.(

0.77

>>;

0.77

SizeMode

0.74

 nahilalakip

0.73

 estekak

0.73

 betweenstory

0.72

Activations Density 0.012%