INDEX

Explanations

properties and dependencies

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

為に

-1.78

ごとの

-1.27

//};

-1.25

aguay

-1.15

 considérable

-1.14

 показывает

-1.13

 ripet

-1.13

 />';

-1.13

ままで

-1.11

様な

-1.10

POSITIVE LOGITS

can

2.27

 should

2.17

is

2.08

 must

1.98

 could

1.94

 will

1.92

may

1.91

 cannot

1.71

 would

1.67

 depends

1.64

Activations Density 0.109%