INDEX

Explanations

numbers and quantities

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

嘞

-1.71

 what

-1.49

 justru

-1.48

 composizione

-1.45

 these

-1.43

 chiusura

-1.42

 soluzioni

-1.39

 things

-1.39

 Mesmo

-1.34

 risposte

-1.33

POSITIVE LOGITS

1.82

1.69

↵↵↵↵

1.53

 ihre

1.52

↵↵↵↵↵↵↵↵↵↵↵

1.51

↵↵↵↵↵

1.48

</em>

1.46

})$,

1.46

↵↵↵↵↵↵↵↵↵↵↵↵↵

1.45

），

1.45

Activations Density 0.076%