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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    words indicating possession and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beg
    -0.71
    hips
    -0.69
    ypes
    -0.67
     IPM
    -0.66
    edd
    -0.64
    orsi
    -0.63
    establishment
    -0.62
    atever
    -0.62
    itement
    -0.60
    ial
    -0.58
    POSITIVE LOGITS
    selves
    1.22
    self
    1.12
    craft
    0.92
    field
    0.80
    fields
    0.78
    opia
    0.76
    cart
    0.74
    creen
    0.73
    urgical
    0.71
    olit
    0.71
    Act Density 0.030%

    No Known Activations