INDEX

Explanations

On Get DR Web input

This neuron detects numeric tokens (counts, IDs, or statistics) typically appearing after colons in structured headings or labels.

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

 this

-2.13

an

-1.69

 tries

-1.57

or

-1.55

As

-1.51

the

-1.45

as

-1.42

for

-1.40

-1.38

 primeras

-1.37

POSITIVE LOGITS

 antiguos

1.59

 interactiva

1.45



1.44

 ENJOY

1.44

 mêmes

1.44

 añad

1.42

 situés

1.41

锲

1.38

四个

1.38

可能です

1.38

Activations Density 0.065%