INDEX

Explanations

positive social values

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

 VOLTAGE

-0.94

וּ

-0.91

vább

-0.89

了出去

-0.88

胛

-0.88

 liné

-0.85

babu

-0.84

着脸

-0.81

 nivå

-0.81

CÓMO

-0.81

POSITIVE LOGITS

 tolerance

2.41

 peace

2.30

 love

2.22

 equality

2.22

 justice

1.84

tolerance

1.80

 Tolerance

1.66

 compassion

1.64

 mutual

1.63

 respect

1.59

Activations Density 0.041%