INDEX

Explanations

words related to crafts, blog posts and time

Blog posts

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

Negative Logits

 iſt

-0.92

 myſelf

-0.87

 Audiodateien

-0.85

 themſelves

-0.84

 Theſe

-0.82

 itſelf

-0.82

 purpoſe

-0.81

 quæ

-0.81

 Majefty

-0.78

 himſelf

-0.76

POSITIVE LOGITS

 didnt

0.88

Whats

0.86

 dont

0.86

Dont

0.83

 thats

0.83

 doesnt

0.83

 couldnt

0.82

 Indias

0.82

 Thats

0.80

 Dont

0.80

Activations Density 1.433%