INDEX

Explanations

a, =

The neuron fires on tokens associated with numeric constants or parameter values (e.g. configuration fields, assignments, or measurements) in code‐ or config‐style listings.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.18

=");

1.18

=$

1.13

1.05

="";

1.03

=(

0.98

='';

0.98

=-

0.96

=(

0.95

++;

0.94

POSITIVE LOGITS

 zebrafish

0.65

 वन्य

0.64

 pickled

0.61

čne

0.61

сынын

0.61

㳓

0.61

सूचित

0.60

 mnoh

0.59

 olfactory

0.59

भो

0.59

Activations Density 0.000%