INDEX

Explanations

made up of

This neuron detects phrases that specify composition by number—especially “made up of” followed by a numeric quantity.

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

-2.36

,”

-2.31

So

-2.09

This

-2.03

of

-1.97

🤪

-1.95

There

-1.95

↵↵

-1.88

In

-1.84

 Jenderal

-1.82

POSITIVE LOGITS

</strong>

2.55

翆

2.38

を使用した

2.20

 WOULD

2.19

跸

2.17

蹀

2.08

 naciones

2.03

趼

2.03

卺

2.03

 แต่

1.98

Activations Density 0.016%