INDEX

Explanations

The neuron fires on personal, “you/I”-style pronouns and direct-address words, marking informal, conversational statements.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

我的

2.16

my

1.83

 mijn

1.81

 我的

1.77

 minha

1.75

 моей

1.74

 나의

1.71

 моя

1.70

 আমার

1.69

私の

1.69

POSITIVE LOGITS

 yourselves

1.94

你们

1.62

 vocês

1.60

你們

1.57

 আপনাদের

1.50

 ustedes

1.43

 jullie

1.42

 Vocês

1.35

 আপনারা

1.34

 Jullie

1.28

Activations Density 0.167%