INDEX

Explanations

quantity or size

The neuron fires on adjectives (and related forms) that express quantitative scope or magnitude—words like “diverse,” “increasing,” “large,” and “small.”

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

 both

-2.09

-1.95

for

-1.85

 their

-1.82

an

-1.81

what

-1.72

to

-1.68

 what

-1.67

or

-1.66

POSITIVE LOGITS

of

2.59

耵

1.91



1.85

 negru

1.82

 dizaines

1.82

 centaines

1.75

 réunions

1.75

 quantités

1.70

聼

1.66

 number

1.66

Activations Density 0.088%