INDEX

Explanations

rankings and positions

This neuron specializes in spotting numeric ranking or placement indicators (e.g., ordinal positions and accompanying numbers in stats).

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

 another

-1.37

 deux

-1.27

 páss

-1.20

があって

-1.16

 одним

-1.15

 другим

-1.15

 altra

-1.13

 принято

-1.13

one

-1.13

χρι

-1.13

POSITIVE LOGITS

in

1.38

 even

1.35

《

1.30

of

1.27

甚至

1.23

 даже

1.21

not

1.17

那些

1.16

at

1.13

 Each

1.12

Activations Density 0.060%