INDEX

Explanations

attempting or exploring

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

是

-3.45

//

-2.97

requipa

-2.78

prende

-2.67

的

-2.66

 sélectionnés

-2.61

gencias

-2.59

 personer

-2.58

 popolo

-2.56

is

-2.52

POSITIVE LOGITS

叹了口气

2.86

看着他

2.72

艄

2.61

蘩

2.55

愠

2.53

を見ながら

2.52

拍了拍

2.52

へ行

2.47

倨

2.44

We

2.42

Activations Density 0.030%