INDEX

Explanations

cake serving ware

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

 капю

-0.87

 Gottlieb

-0.83

 tigre

-0.83

 shouldBe

-0.81

 curtains

-0.78

 antibodies

-0.78

ligere

-0.78

 DataGridView

-0.77

граф

-0.77

 fabrik

-0.77

POSITIVE LOGITS

 serving

1.68

 Serving

1.40

serving

1.26

Serving

1.25

 vase

0.97

 vases

0.94

 watering

0.92

watering

0.92

 coffee

0.86

 drinking

0.83

Activations Density 0.021%