INDEX

Explanations

to initiate

The neuron consistently fires on occurrences of the verb “initiated” (and its close variants) marking the start of an action or project.

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

 decidedly

-2.55

we

-2.55

</strong>

-2.45

雱

-2.31

 Zuhause

-2.31

 poświę

-2.25

";

-2.25

she

-2.23

𝐧

-2.20

 senhor

-2.19

POSITIVE LOGITS

 時尚

2.91



2.53

鏨

2.45

メリカ

2.31

 unrelenting

2.30

?”

2.28

㌧

2.25

ଃ

2.25

 現貨

2.23

袿

2.22

Activations Density 0.011%