INDEX

Explanations

describing qualities of nouns

The neuron activates on descriptive adjective words (i.e. modifiers that characterize or qualify nouns).

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

if

-1.59

 because

-1.52

ppsala

-1.43

 some

-1.37

as

-1.34

.\\

-1.30

 then

-1.29

has

-1.28

==",

-1.27

on

-1.26

POSITIVE LOGITS

 этого

1.58

 ولكن

1.46

This

1.46

 banane

1.39

どうして

1.38

其他的

1.36

唯一的

1.32

っちゃった

1.32

 लेकिन

1.31

合作伙伴

1.30

Activations Density 0.193%