INDEX

Explanations

centuries BCE AD CE BC

This neuron fires on short uppercase abbreviations (like “ACP,” “Auto,” “CE,” etc.), i.e. brief all-caps tokens often used as units, model codes, or era markers.

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

 }));

-1.58

})),

-1.51

#(

-1.49

"});

-1.47

푔

-1.46

ÃO

-1.45

ates

-1.41

镡

-1.38

 shopee

-1.38

CEAN

-1.38

POSITIVE LOGITS

 result

1.65

 Ergebnis

1.41

1.38

 bereits

1.38

↵

1.33

 результат

1.31

 takiej

1.28

↵↵

1.27

 Along

1.27

งาน

1.23

Activations Density 0.053%