INDEX

Explanations

locations, addresses, or codes

The neuron fires on geographic place names (city, state, street, or venue names) in address or location contexts.

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

-1.70

</em>

-1.17

-1.16

SOUNDBITE

-1.15

-1.13

-1.00

 schrijven

-0.99

}^{

-0.99

<em>

-0.97

POSITIVE LOGITS

Zubereitung

1.33

 will

1.30

Beskrivelse

1.28

чении

1.23

southeast

1.22

จะมี

1.22

Suara

1.20

northeast

1.14

ῖς

1.09

ωμα

1.09

Activations Density 0.001%