INDEX

Explanations

multilingual temporal markers

The neuron is strongly activated by common English function words (especially auxiliaries, pronouns, prepositions, and comparative markers).

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

-1.63

嫆

-1.41

瑒

-1.39

sistence

-1.36

໊

-1.29

}$;

-1.28

 County

-1.26

穡

-1.25

$\

-1.23

 spolup

-1.23

POSITIVE LOGITS

out

1.26

的时候

1.25

 before

1.23

 כבר

1.20

 forskjellige

1.18

也不是

1.17

 verdaderos

1.16

 intereses

1.16

 다른

1.16

：「

1.15

Activations Density 0.004%