INDEX

Explanations

words and phrases related to legal or scientific documents

expressions of causation or conclusion

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

Negative Logits

UnknownFieldSet

-0.73

 initComponents

-0.73

DoubleQuotes

-0.72

存于互联网档案馆

-0.72

astéroïdes

-0.71

InjectAttribute

-0.71

 createState

-0.70

 myſelf

-0.69

 الحره

-0.69

 utafitiHapana

-0.68

POSITIVE LOGITS

so

2.67

 thus

2.02

so

1.91

 così

1.72

thus

1.66

So

1.55

 Thus

1.55

 así

1.53

Thus

1.52

So

1.50

Activations Density 3.477%