INDEX

Explanations

some

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.72

 protoimpl

-0.67

 مرئيه

-0.65

 تانيه

-0.64

AccessorTable

-0.57

 ffilm

-0.55

-0.52

же

-0.46

WebServlet

-0.46

dhury

-0.45

POSITIVE LOGITS

 cases

0.99

 instances

0.72

cases

0.69

 Cases

0.67

 ways

0.65

 manner

0.64

 contexts

0.64

way

0.63

 circumstances

0.62

 przypad

0.62

Activations Density 0.067%