INDEX

Explanations

where clauses

The neuron is selectively activating on numeric tokens that include decimal points.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

mov

1.35

me

1.34

is

1.27

ları

1.26

ल

1.23

mét

1.22

mobili

1.13

 gange

1.13

א

1.12

וס

1.11

POSITIVE LOGITS

})\

1.30

}+\

1.29

ﯼ

1.26

}=$

1.23

fledged

1.23

ки

1.22

〢

1.19

 मेगापिक्सल

1.16

 herring

1.14

fowl

1.12

Activations Density 0.080%