INDEX

Explanations

punctuation and names

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

-1.56

讓我

-1.47

給我

-1.43

বং

-1.32

 отды

-1.27

 蔬菜

-1.25

 naše

-1.24

美味しく

-1.24

誒

-1.23

 enggak

-1.21

POSITIVE LOGITS

 with

1.46

 without

1.35

 είχε

1.34

₱

1.34

 растений

1.33

}');

1.29

 knew

1.27

 ideia

1.26

 pemeriksaan

1.25

 blive

1.24

Activations Density 0.007%