INDEX

Explanations

manage something specific

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

Erstellt

-1.84

ༀ

-1.75

ギュア

-1.70

僦

-1.66

꯵

-1.62

 denkt

-1.55

ISING

-1.54

蛱

-1.53

🌷

-1.52

 belangrijke

-1.51

POSITIVE LOGITS

of

2.81

 There

1.84

1.73

While

1.73

?"

1.68

After

1.61

 подход

1.59

？”

1.57

地在

1.56

up

1.53

Activations Density 0.005%