INDEX

Explanations

consent and consensual topics

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

изнь

-0.82

 блюда

-0.71

 insecure

-0.71

zong

-0.69

food

-0.68

jc

-0.68

сота

-0.67

:=

-0.67

demo

-0.66

 اثر

-0.66

POSITIVE LOGITS

 consens

4.53

 consenting

3.70

 consent

3.30

 consented

3.08

 Consent

2.77

consent

2.77

Consent

2.63

 voluntary

2.48

 consents

2.36

 willingly

2.09

Activations Density 0.048%