INDEX

Explanations

witnesses and testimony

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

的作品

-0.84

 verbe

-0.78

 Beginners

-0.73

iana

-0.71

 Siga

-0.70

 '+':

-0.70

vur

-0.69

 Visite

-0.68

 تشخیص

-0.68

 khuôn

-0.68

POSITIVE LOGITS

 witnesses

5.66

 witness

5.09

witness

3.59

Witnesses

3.55

 Witnesses

3.52

 Witness

3.47

Witness

3.39

 WITNESS

3.17

 свиде

3.03

 testigos

2.92

Activations Density 0.040%