INDEX

Explanations

statements about confidentiality and data protection

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ar

-0.48

 less

-0.46

сер

-0.46

ar

-0.45

 fore

-0.43

 motion

-0.43

Ar

-0.43

van

-0.43

 random

-0.42

POSITIVE LOGITS

identiality

1.23

 Confidentiality

1.04

 Confidential

1.03

PerformLayout

1.02

Confidential

0.99

EndProject

0.97

 confidentiality

0.95

mobileqq

0.91

 confidential

0.87

تقاوى

0.87

Activations Density 0.011%