INDEX

Explanations

The neuron fires on numeric tokens—especially numbers (often with decimal points) in tabular or data‐table 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

No Comments

Negative Logits

-1.73

of

-1.59

jangkau

-1.51

Hlav

-1.48

-1.46

從

-1.44

your

-1.44

 aptly

-1.43

 calefacción

-1.41

Моя

-1.38

POSITIVE LOGITS

</td>

1.98

 nyní

1.66

了很多

1.59

 потому

1.55

 اگر

1.55

 Relaciones

1.53

 svou

1.52

戗

1.45

</h5>

1.45

Activations Density 0.004%