INDEX

Explanations

references to experiencing injury or harm

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

 suffering

-1.11

 Suffering

-0.92

suffering

-0.73

zeba

-0.63

DoubleQuotes

-0.57

 насељу

-0.54

 sufferings

-0.54

ffering

-0.52

 established

-0.50

 приме

-0.50

POSITIVE LOGITS

 suffered

1.43

 undergone

0.90

 sufrió

0.81

 sufrido

0.75

 endured

0.70

 struggled

0.68

viewDidLoad

0.60

hoeddwyd

0.60

CloseOperation

0.59

LookAnd

0.57

Activations Density 0.005%