INDEX

Explanations

both or each followed by noun

This neuron detects binary quantifier constructions—words that refer to two items in tandem (e.g. “both,” “each,” “either”).

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

ほとん

-1.46

さんへ

-1.40

even

-1.37

 nawet

-1.30

櫻

-1.30

 mesmo

-1.29

やう

-1.28

 всі

-1.28

 even

-1.27

 намного

-1.26

POSITIVE LOGITS

are

1.42

 have

1.39

 butterknife

1.38

was

1.34

has

1.34

 свои

1.33

 получили

1.27

是

1.26

chenke

1.24

 был

1.22

Activations Density 0.078%