INDEX

Explanations

citation closing brackets and followed by `@`

The neuron detects in‐text scholarly citation markers (e.g. bracketed reference numbers or alphanumeric citations).

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

 neuf

-1.67

 särsk

-1.45

 other

-1.39

vux

-1.36

 meiner

-1.32

 pieni

-1.32

-1.30

 creciendo

-1.30

 cercle

-1.29

omás

-1.25

POSITIVE LOGITS

</h2>

1.79

1.50

and

1.46

 septembrie

1.36

hdysval

1.33

帳に追加

1.33

as

1.28

chiato

1.27

—

1.26

手上

1.26

Activations Density 0.050%