INDEX

Explanations

city names or locations

The neuron chiefly activates on place names (particularly city names) in the text.

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

 their

-1.59

and

-1.53

 this

-1.51

or

-1.48

お楽しみに

-1.35

Գ

-1.32

 perdido

-1.30

corrhi

-1.29

 that

-1.27

 Using

-1.27

POSITIVE LOGITS

などが

1.62

なので

1.58

があるので

1.44

という感じ

1.41

<bos>

1.41

 alcune

1.38

がありますが

1.38

もあって

1.38

などを

1.33

などは

1.28

Activations Density 0.026%