INDEX

Explanations

addon

The neuron is primarily triggered by occurrences of the term “addon” (e.g. in file paths or code references).

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

ſſel

-2.56

衚

-2.50

渽

-2.41

 Hinblick

-2.38

of

-2.36

-2.31

-2.27

ਞ

-2.22

⸰

-2.22

ultuous

-2.22

POSITIVE LOGITS

↵↵

3.05

萏

2.50

 améli

2.47

 Notably

2.31

ра

2.30

ifikant

2.30

渼

2.27

 wenn

2.23

 Other

2.20

 Carefully

2.16

Activations Density 0.002%