Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive adjectives indicating relationships between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¼ij
    -0.18
    archive
    -0.15
    ová
    -0.15
    ildo
    -0.14
    iom
    -0.14
    abar
    -0.14
    าà¸Ķ
    -0.13
     chests
    -0.13
    otty
    -0.13
     sofas
    -0.13
    POSITIVE LOGITS
     phone
    0.22
     arms
    0.20
     surroundings
    0.20
     gaze
    0.20
     peripheral
    0.19
     coat
    0.18
     attention
    0.18
     footing
    0.18
     thoughts
    0.18
     quarry
    0.17
    Act Density 0.211%

    No Known Activations