INDEX

Explanations

mathematical formulas and numbers

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

ushin

-0.76

كويكب

-0.71

Huf

-0.69

 EClass

-0.68

Eb

-0.67

 Brot

-0.66

 depth

-0.65

Bü

-0.65

EClass

-0.65

 Schub

-0.65

POSITIVE LOGITS

 Warne

0.78

szön

0.71

ReusableCell

0.71

 Tarn

0.69

 Martine

0.68

ậc

0.65

LDA

0.64

NLR

0.63

 Lear

0.63

ksikon

0.63

Activations Density 0.157%