INDEX

Explanations

code and data manipulation

This neuron fires on code expressions invoking methods or API calls (e.g. chained function calls like .collection(), .append(), .selectAll(), etc.).

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

ícias

-1.60

もあった

-1.46

 geralmente

-1.37

niños

-1.36

为什么

-1.35

 powinno

-1.34

 serão

-1.34

 essas

-1.32

</h3>

-1.31

 cuja

-1.31

POSITIVE LOGITS

kelig

1.31

новение

1.30

 that

1.26

錞

1.26

to

1.26

၅

1.24

 this

1.24

기를

1.20

cknow

1.20

 grandeur

1.16

Activations Density 0.021%