INDEX

Explanations

code keywords or types

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

-2.20

 erstes

-2.14

 Besonder

-2.00

‘

-1.98

are

-1.94

 zweiter

-1.85

et

-1.84



-1.80

}{

-1.78

 siendo

-1.72

POSITIVE LOGITS

of

2.16

趼

2.11

𓆜

1.92

 放題

1.79

퐹

1.77

мент

1.71

沨

1.69

 princesa

1.66

𓐍

1.66

 majesty

1.63

Activations Density 0.002%