INDEX

Explanations

sections of groups

The neuron activates on nouns that denote statistical subdivisions or groupings (e.g. “section,” “segment,” “population,” “quarters”).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

֎

-1.44

 molte

-1.44

鲥

-1.39

 facendo

-1.36

 ciasc

-1.35

 entrambi

-1.32

 chacune

-1.29

GEBUR

-1.27

 лично

-1.26

sern

-1.24

POSITIVE LOGITS

of

1.59

 those

1.53

 поколения

1.45

DispatchToProps

1.44

\{

1.43

⑊

1.42

 naszej

1.39

 people

1.38

ISOString

1.38

\\

1.38

Activations Density 0.032%