INDEX

Explanations

dual reporter

The neuron fires on numeric tokens—individual digits (and digit‐heavy strings, like IDs) in the text.

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

and

-2.19

They

-2.14

for

-1.90

or

-1.80

 với

-1.78

These

-1.75

-1.73

 With

-1.65

！"

-1.59

Они

-1.56

POSITIVE LOGITS

犼

1.92

)};

1.91

 beiden

1.88

)();

1.87

_;

1.86

 innymi

1.80

érales

1.77

”،

1.75

celotti

1.74

珰

1.74

Activations Density 0.000%