INDEX

Explanations

welcome

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

 утвер

-0.75

 invasión

-0.69

خوری

-0.69



-0.68

салат

-0.66

ปิด

-0.66

Nilai

-0.66

럴

-0.66

лід

-0.66

 showdown

-0.65

POSITIVE LOGITS

 welcome

8.19

Welcome

7.19

 Welcome

7.16

welcome

6.53

 WELCOME

5.56

WELCOME

5.22

 welcomed

5.03

 welcomes

5.00

欢迎

4.72

 welcoming

4.22

Activations Density 0.204%