INDEX

Explanations

Street Journal, Colombo, brown, wagon

The neuron is detecting document‐level metadata tokens—things like dateline markers (dates, locations, sources in parentheses), section or headline names, footnote/citation symbols, event or media outlet titles—rather than ordinary running text.

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

sukienka

-2.33

台中

-2.23

เรา

-2.19

-2.17

𝕻

-2.06

leopard

-2.05

 間取り

-2.05

kurtka

-2.03

 provides

-2.02

Guinea

-2.02

POSITIVE LOGITS

…….

2.81

他能

2.70

2.66

就得

2.53

….

2.53

The

2.50

……..

2.47

 Similarly

2.42

،

2.41

ным

2.38

Activations Density 0.001%