INDEX

Explanations

descriptive terms followed by context

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

in

-2.30

of

-1.96

)++;

-1.81

to

-1.81

-1.69

 like

-1.61

䜣

-1.58

we

-1.55

 naudo

-1.52

𐑂

-1.52

POSITIVE LOGITS

 extraordinaire

1.57

 потім

1.55

 thingy

1.54

ल

1.52

Ꭿ

1.46

 apartament

1.45

 whichever

1.44

 будет

1.43

 câbles

1.42

ゔ

1.41

Activations Density 0.248%