INDEX

Explanations

describing different sizes

The neuron fires on mentions of “sizes,” i.e. tokens referring to dimensional or size specifications.

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

-2.72

to

-2.69

-2.67

-2.41

For

-2.41

</td>

-2.38

 verdaderamente

-2.31

-2.20

↵↵

-2.20

it

-2.16

POSITIVE LOGITS

of

2.72

 sizes

2.72

."

2.58

sizes

2.50

atief

2.45

喜欢的

2.31

 fabricants

2.30

豨

2.27

 acheteurs

2.23

癭

2.19

Activations Density 0.010%