INDEX

Explanations

children and kids

The neuron flags mentions of children (e.g. “kids,” “children,” or child‐related age contexts).

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

by

-1.80

in

-1.66

so

-1.55

 there

-1.36

 they

-1.32

for

-1.30

Exeunt

-1.22

宝宝

-1.22

we

-1.20

 including

-1.20

POSITIVE LOGITS

ሦ

1.48

、

1.35

 leichter

1.33

 этом

1.32

 dolu

1.30

蟶

1.30

 havde

1.28

 ähn

1.28

 großem

1.24

 vorhand

1.23

Activations Density 0.094%