INDEX

Explanations

route definitions and web code

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

これからの

-1.85

余談

-1.78

現状

-1.76

 leopardo

-1.67

 perpé

-1.67

 démission

-1.66

やりたい

-1.65

 bisous

-1.65

次回は

-1.64

 unicornio

-1.63

POSITIVE LOGITS

and

2.14

</i>

1.86

1.64

1.57

？

1.55

><

1.53

。（

1.51

1.49

by

1.48

as

1.47

Activations Density 0.001%