INDEX

Explanations

numerical lists and codes

The neuron activates on standalone numeric tokens—digits or number sequences (e.g. “5,” “74,” “16.125”)—i.e. it detects numbers.

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

our

-1.49

を中心

-1.40

 ocurrió

-1.38

 Национальный

-1.37

 beliebt

-1.34

 praca

-1.33

 podremos

-1.31

 komentar

-1.31

-1.30

-1.29

POSITIVE LOGITS

↵↵

1.63

1.56

 tienen

1.51

当前

1.51

1.49

三个

1.48

</td>

1.43

 formulario

1.41

”。

1.37

entown

1.36

Activations Density 0.058%