INDEX

Explanations

car parts

The neuron fires on references to looking under or into vehicle body parts—especially the hood (and similar “under the hood” contexts) of cars and trucks.

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

这些

-1.62

)」

-1.58

)\

-1.55

 prétend

-1.51

如何

-1.45

這些

-1.38

}$;

-1.38

」，

-1.36

 работал

-1.35

POSITIVE LOGITS

You

1.54

we

1.52

 your

1.48

’

1.42

 about

1.38

鲤

1.29

We

1.27

 ตาม

1.26

啖

1.25

 futile

1.23

Activations Density 0.025%