INDEX

Explanations

the word "mainstream."

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

WindowConstants

-0.87

ifel

-0.80

awtextra

-0.79

farin

-0.75

pedia

-0.71

Kud

-0.71

feira

-0.70

 Photocase

-0.69

atoga

-0.69

 Goodwin

-0.69

POSITIVE LOGITS

 mainstream

1.16

主流

0.73

ing

0.65

uscita

0.64

 consciousness

0.63

STREAM

0.63

estream

0.63

 Theſe

0.63

 houſe

0.62

 becauſe

0.59

Activations Density 0.002%