INDEX

Explanations

The neuron fires on direct user‐address marketing prompts—especially question‐style calls to action (e.g. “Are you looking for…?”).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

or

0.94

and

0.87

0.85

0.84

0.82

at

0.80

0.75

0.74

--

0.72

POSITIVE LOGITS

 Général

0.84

一個

0.78

 وهو

0.74

 zudem

0.74

 Seorang

0.73

 એક

0.73

 மற்றொரு

0.73

 انہیں

0.73

 allerdings

0.72

 सुद्धा

0.72

Activations Density 0.001%