INDEX

Explanations

memory and its qualities

The neuron fires on words referring to memory or remembering—e.g. “memory,” “memories,” “remember.”

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

}$.

-1.52

-1.40

-1.32

π

-1.24

-1.23

).

-1.22

 according

-1.21

-1.20

ne

-1.18

POSITIVE LOGITS

 kupa

1.48

 recollection

1.46

Significance

1.41

 memories

1.40

 можуть

1.39

 Imágenes

1.34

 several

1.32

issants

1.32

 ſeveral

1.31

 手提

1.30

Activations Density 0.057%