INDEX

Explanations

ending life

The neuron activates on words describing the act of killing or euthanizing (especially “euthanize,” “euthanized,” “euthanasia,” etc.).

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

capulco

-1.49

complish

-1.48

これに

-1.41

 EVERYTHING

-1.41

 IIRC

-1.38

 cuya

-1.38

 herrera

-1.37

ﻡ

-1.37

 död

-1.34

茛

-1.34

POSITIVE LOGITS

1.88

 part

1.77

1.69

 freundlichen

1.45

anasia

1.43

 Tuesday

1.42

by

1.39

 beinahe

1.38

เพื่อ

1.37

Activations Density 0.017%