INDEX

Explanations

declaration of invention

The neuron activates on numeric tokens—integers, decimals, and other digit sequences.

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

嗖

-1.63

and

-1.42

ll

-1.38

子的

-1.35

for

-1.35

 државе

-1.34

but

-1.30

}$

-1.30

langkah

-1.30

 parfüm

-1.30

POSITIVE LOGITS

烔

1.46



1.46

揹

1.44

 optimale

1.41

廡

1.40

⚢

1.39

鵙

1.38

𓋼

1.38

yship

1.36

琍

1.35

Activations Density 0.001%