INDEX

Explanations

references to North Korea and Kim Jong-un

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

 تانيه

-0.79

parsedMessage

-0.65

YY

-0.61

 Banten

-0.58

 ©️

-0.57

 defStyleAttr

-0.57

 privilégi

-0.57

 igenom

-0.57

 juſ

-0.57

nextDouble

-0.56

POSITIVE LOGITS

 Jong

0.80

 Pyongyang

0.74

ongyang

0.71

nitus

0.66

Jong

0.64

 Papier

0.60

>*/

0.56

SuppressLint

0.56

 ElementRef

0.54

 Paper

0.54

Activations Density 0.004%