INDEX

Explanations

authentic, true, historical

The neuron detects words and phrases that signal factual or “based on a true story” content (e.g., real, true, based on, actual, bio).

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

Di

-0.93

et

-0.92

十

-0.90

腹部

-0.88

('/',

-0.85

_{\

-0.85

 focal

-0.84

耕

-0.83

 Silva

-0.83

 varchar

-0.82

POSITIVE LOGITS

 реаль

2.34

 real

2.20

 واقعی

1.90

 actual

1.84

真实

1.78

จริง

1.74

 echten

1.65

真實

1.63

 réel

1.59

真实的

1.59

Activations Density 0.061%