INDEX

Explanations

course or safety training

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

हो

-0.75

JY

-0.71

 której

-0.71

лежки

-0.70

NIST

-0.70

CLAR

-0.69

 Landsat

-0.68

crom

-0.67

 grav

-0.67

Cascade

-0.67

POSITIVE LOGITS

 courses

1.52

 course

1.49

 classes

1.30

课程

1.20

 kurs

1.13

 cursos

1.12

Course

1.11

course

1.11

Courses

1.11

 safety

1.10

Activations Density 0.025%