INDEX

Explanations

preloading data or components

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

we

-2.72

 scrive

-2.34

 chiede

-2.34

It

-2.33

-2.25

 termed

-2.23

先前

-2.23

 bestätigt

-2.23

瓩

-2.20

 voleva

-2.17

POSITIVE LOGITS

 они

3.14

ll

2.73

llavero

2.47

又不

2.42

玙

2.39

sandalia

2.38

钤

2.31

읗

2.19

他们的

2.17

 нескольких

2.17

Activations Density 0.003%