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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships, particularly focusing on loved ones

    oai_token-act-pair · gpt-3.5-turbo

    references to loved ones and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.75
    ulated
    -0.73
    ilion
    -0.67
    soDeliveryDate
    -0.67
     Regulatory
    -0.66
    irin
    -0.64
    UL
    -0.64
    ipl
    -0.63
    uration
    -0.63
    raz
    -0.63
    POSITIVE LOGITS
     dearly
    0.95
     uncond
    0.88
     loved
    0.87
    ometown
    0.87
     ones
    0.84
     nephew
    0.84
     pets
    0.82
    liest
    0.81
     spouse
    0.77
     grandchildren
    0.77
    Act Density 0.054%

    No Known Activations