INDEX

Explanations

Python special method names

The neuron fires on Python identifiers that begin with an underscore (i.e. “private” or internal names).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 direta

-1.77

 felicidade

-1.69

 chaleco

-1.66

違った

-1.65

很赞

-1.63

 decoracion

-1.63

 llavero

-1.63

鏐

-1.62

 olhando

-1.61

 romántico

-1.61

POSITIVE LOGITS

of

2.13

2.06

</b>

1.98

");

1.88

</em>

1.87

</

1.80

ie

1.77

</i>

1.73

 suoi

1.69

AL

1.67

Activations Density 0.002%