INDEX

Explanations

technical descriptions and definitions

This neuron detects technical code or query terms—especially identifiers for variables, functions, parameters, and placeholders (including ordinal markers like “1st,” “2nd”)—in programming contexts.

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

 estructuras

-1.36

 komplett

-1.27

 modificaciones

-1.26

 EconPapers

-1.26

 gyors

-1.24

 cualidades

-1.23

 divertido

-1.23

 seura

-1.22

Více

-1.20

 surpren

-1.20

POSITIVE LOGITS

 which

2.80

by

1.91

in

1.74

of

1.63

 with

1.52

and

1.44

 because

1.39

 like

1.38

 also

1.38

 therefore

1.34

Activations Density 0.433%