INDEX

Explanations

the word "whose"

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

is

-0.66

raltar

-0.60

-0.59

 will

-0.59

 ever

-0.57

per

-0.57

 MenuView

-0.56

-0.55

 leerlingen

-0.54

so

-0.52

POSITIVE LOGITS

 whoſe

1.20

 whofe

1.18

 Whose

1.11

Whose

1.08

 Houſe

1.02

 Theſe

1.00

 ་་

0.98

whose

0.96

$[-

0.94

 Conſ

0.90

Activations Density 0.010%