INDEX

Explanations

burial and interment

The neuron activates on words related to burial or interment (e.g., “burial,” “buried”).

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

 και

-2.28

 gadis

-2.11

/>;

-2.05



-2.02

//}

-2.00

 '');

-1.99

"&

-1.98

&&

-1.94

 perjuangan

-1.91

他就

-1.87

POSITIVE LOGITS

 paramount

2.23

ные

2.22

ں

2.20

齪

2.20

2.16

 concerted

2.11

たまた

2.03

<bos>

1.94

 conscious

1.92

 unequal

1.91

Activations Density 0.002%