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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships or belonging

    oai_token-act-pair · gpt-3.5-turbo

    references to personal possession or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.77
    hips
    -0.73
    iencies
    -0.63
     Beg
    -0.63
    establishment
    -0.63
    ITIES
    -0.63
    ITY
    -0.63
    trump
    -0.62
    atever
    -0.61
    ulation
    -0.60
    POSITIVE LOGITS
    craft
    1.08
    opia
    0.95
    self
    0.92
    selves
    0.87
    field
    0.86
    heim
    0.85
    ovie
    0.78
    fields
    0.77
    cart
    0.75
    stic
    0.73
    Act Density 0.007%

    No Known Activations