INDEX

Explanations

the prefix "hom" followed by another word

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

\{\\

-0.80

claimer

-0.69

ogeneous

-0.66

vided

-0.65

 Hati

-0.65

actrice

-0.64

vul

-0.63

 Schar

-0.63

 Holtz

-0.63

исленность

-0.62

POSITIVE LOGITS

hom

1.38

hom

1.16

Hom

1.16

Hom

1.14

HOM

0.91

HOM

0.88

 homo

0.86

 homestay

0.85

 Homestead

0.82

gamesh

0.81

Activations Density 0.022%