INDEX

Explanations

moved to, living in, turned

The neuron fires on verbs and phrases indicating a person’s relocation or immigration (e.g., “living in,” “emigrated to,” “moved to”).

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

 emailAlready

-1.02

 another

-0.99

唳

-0.98

 enfin

-0.97

 方案

-0.95

 השני

-0.94

ophanes

-0.94

⅘

-0.93

 chaussures

-0.93

それも

-0.92

POSITIVE LOGITS

隨著

1.05

to

1.05

После

1.02

ഒ

0.93

 after

0.91

近年来

0.90

美國

0.90

近年

0.90

Após

0.87

//}

0.86

Activations Density 0.091%