INDEX

Explanations

plural nouns ending categories

The neuron fires on words that set up dual or paired comparisons—e.g. “both,” “two,” and similar markers of a two-way enumeration.

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

and

-2.31

 even

-1.58

for

-1.50

all

-1.35

 also

-1.32

not

-1.31

 just

-1.31

in

-1.31

 only

-1.29

 like

-1.24

POSITIVE LOGITS

 reú

1.44

 depois

1.38

ЛИ

1.33

蓠

1.31

 salvare

1.28

óta

1.27

头上

1.24

*{-

1.23

 angek

1.23

Activations Density 0.140%