INDEX

Explanations

learning specific subjects

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

it

-1.82

-1.67

惋

-1.57

 первая

-1.46

踏み

-1.36

 девя

-1.35

 vingt

-1.34

us

-1.34

たつ

-1.33

 nachts

-1.27

POSITIVE LOGITS

();

1.76

valents

1.60

");

1.47

 skills

1.45

'];

1.44

 $^{\

1.43

」、「

1.41

oaks

1.38

.,"

1.38

 tessuto

1.37

Activations Density 0.020%