INDEX

Explanations

people's needs and actions

The neuron sharply activates on occurrences of the word “people.”

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

the

-2.28

tabol

-1.59

 they

-1.51

 abogados

-1.43

êter

-1.40

 their

-1.39

.”

-1.39

its

-1.39

 vacacionales

-1.30

rokken

-1.29

POSITIVE LOGITS

：……

1.73

%;

1.33

<td>

1.32

浹

1.32

 startY

1.31

vgili

1.27

 каже

1.27

dare

1.25

吗

1.23

and

1.23

Activations Density 0.043%