INDEX

Explanations

punctuation followed by terms

The neuron is triggered by mathematical/expression tokens—operators (like “*” and “/”) and math context words (e.g. “assuming”) in algebraic formulas.

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

幾個

-1.68

選ぶ

-1.30

地圖

-1.29

フラット

-1.25

三個

-1.22

 crucified

-1.21

 einzige

-1.17

jenige

-1.16

 Comunidad

-1.16

点此

-1.16

POSITIVE LOGITS

we

1.78

</strong>

1.65

）.

1.54

 beider

1.45

’,

1.42

siamo

1.41

empio

1.40

 zobaczyć

1.38

klü

1.38

she

1.35

Activations Density 0.465%