INDEX

Explanations

the phrase once again

This neuron detects the phrase “once again.”

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

-1.41

्व

-1.37

無法

-1.31

 vacía

-1.30

følge

-1.29

-1.27

 jendela

-1.27

細節

-1.26

他有

-1.25

POSITIVE LOGITS

},

1.68

>}

1.58

 again

1.55

 further

1.53

$-

1.48

ruguay

1.48

mettre

1.47

zné

1.47

chien

1.46

Skocz

1.45

Activations Density 0.018%