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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding morality and accountability in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reur
    -0.15
    efs
    -0.15
    _notifier
    -0.14
    ROP
    -0.14
    ="?
    -0.14
    ureau
    -0.13
    portun
    -0.13
    не
    -0.13
    phe
    -0.13
    ayan
    -0.13
    POSITIVE LOGITS
    BB
    0.15
    rieg
    0.14
    ibold
    0.14
     Schmidt
    0.14
    Ñīин
    0.14
     Leaves
    0.13
     Gross
    0.13
    oric
    0.13
    hores
    0.13
    ernal
    0.13
    Act Density 0.869%

    No Known Activations