INDEX

Explanations

another name, person, part, way

This neuron fires on instances of the word “another” followed by a noun (e.g. “another way,” “another World,” “another person”).

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

 estadounid

-2.06

 纹身

-1.82

其他人

-1.81

-1.69

 قه

-1.62

-1.61

 短发

-1.61

 عسل

-1.54

睜

-1.53

توضی

-1.52

POSITIVE LOGITS

 than

2.56

₁)

1.78

idopsis

1.67

RenderAtEndOf

1.67

 могут

1.63

StoryboardSegue

1.61

)",

1.59

怍

1.52

);

1.51

 на

1.49

Activations Density 0.047%