INDEX

Explanations

loop counters i, j, x

The neuron responds to numeric literal tokens in code, especially numbers used in loop headers (e.g., initializers, bounds, and increments).

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

 them

-1.52

or

-1.52

re

-1.49

 उन्हें

-1.48

st

-1.44

//

-1.41

all

-1.39

by

-1.35

 mereka

-1.34

POSITIVE LOGITS

 گذاری

2.03

 betrifft

1.59

are

1.57

饧

1.48

 ermöglicht

1.43

 such

1.43

謖

1.41

玗

1.41

 pequena

1.41

にした

1.39

Activations Density 0.004%