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

    Neuronpedia

    INDEX
    Explanations

    names of political figures, especially female ones

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Carly Fiorina and Melania Trump, in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obe
    -0.78
    aughs
    -0.74
    ells
    -0.72
    ochond
    -0.70
    EngineDebug
    -0.69
    apest
    -0.69
    olver
    -0.68
    rafted
    -0.67
    ovie
    -0.66
    UGC
    -0.66
    POSITIVE LOGITS
     Fiorina
    1.31
     Melania
    0.91
     Christina
    0.86
    mma
    0.76
    metics
    0.74
    plate
    0.71
    ulia
    0.70
     Carly
    0.70
     maiden
    0.69
    zza
    0.68
    Act Density 0.022%

    No Known Activations