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

    Neuronpedia

    INDEX
    Explanations

    relationships with family members

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial relationships, particularly those involving brothers-in-law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.69
    llan
    -0.64
     campuses
    -0.61
     gob
    -0.60
     drained
    -0.60
     swall
    -0.58
    alach
    -0.57
     milestones
    -0.56
    AMY
    -0.56
     Wow
    -0.55
    POSITIVE LOGITS
    iti
    0.83
    vention
    0.78
    ventions
    0.77
    ordinate
    0.75
    vent
    0.75
     exile
    0.72
    jured
    0.72
    uty
    0.72
    structed
    0.71
    sole
    0.71
    Act Density 0.060%

    No Known Activations