INDEX

Explanations

Nelson, or names containing Nelson

The neuron activates strongly on occurrences of the proper name “Nelson.”

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

-3.66

 данной

-2.45

 案内

-2.39

 уровне

-2.36

 outrage

-2.34

 halt

-2.34

昞

-2.31

 Bagaimana

-2.30

äiv

-2.27

齪

-2.23

POSITIVE LOGITS

ра

2.52

もお

2.48

佧

2.45

部分が

2.27

 Then

2.23

が広

2.19

suo

2.14



2.13

からお

2.13

</em>

2.13

Activations Density 0.003%