INDEX

Explanations

create, find, select, new, where

The neuron fires on the double‐colon scope/resolution operator “::” in code, marking class-or-module method calls or namespace references.

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

-1.27

to

-1.26

The

-1.23

-1.20

-1.13

-1.09

翔

-1.08

POSITIVE LOGITS

 proyección

1.35

癭

1.24

 corriger

1.24

 granos

1.19

をした

1.18

 cóc

1.16

 ventilación

1.16

 colocación

1.15

 elevación

1.14

饜

1.14

Activations Density 0.004%