INDEX

Explanations

reality tv show

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

the

-1.76

<bos>

-1.63

),

-1.53

 Even

-1.47

 Especially

-1.41

 Даже

-1.41

旁边

-1.41

},

-1.40

And

-1.38

 Notably

-1.37

POSITIVE LOGITS

 rendus

1.93

 définiti

1.75

 présentés

1.73

 incele

1.70

 ieder

1.67

𝐧

1.62

 élevés

1.62

真正

1.58

 acheteurs

1.56

 merasakan

1.54

Activations Density 0.010%