INDEX

Explanations

possessive pronouns or articles followed by nouns

This neuron does not consistently activate on any particular token or pattern.

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

 know

-2.20

に行く

-2.00

geſ

-1.95

you

-1.92

 Перейти

-1.87

 deudas

-1.82

 tajem

-1.81

био

-1.80

 advirtió

-1.79

andidat

-1.78

POSITIVE LOGITS

2.83

2.67

2.53

2.23

2.19

.”

2.03

嗵

2.02

an

1.98

我们

1.95

}=

1.89

Activations Density 0.006%