INDEX

Explanations

comparing diverse things

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

聍

-2.06

of

-2.05

を変える

-1.86

öf

-1.78

THERE

-1.73

唖

-1.73

侂

-1.72

でもいい

-1.71

ſtra

-1.71

 zarówno

-1.69

POSITIVE LOGITS

1.75

ں

1.63

<bos>

1.59

 that

1.54

 touted

1.52

hålla

1.50

 initiatives

1.47

 pushes

1.45

 plethora

1.41

 piscinas

1.41

Activations Density 0.019%