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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and their titles

    oai_token-act-pair · gpt-3.5-turbo

    references to public figures in leadership roles, specifically First Ladies and ministers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAY
    -0.79
    STD
    -0.72
    Hour
    -0.71
    amaz
    -0.70
     Manson
    -0.67
    roe
    -0.67
    thirst
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    gm
    -0.64
    strous
    -0.64
    POSITIVE LOGITS
    ©¶æ
    0.72
    ħĭ
    0.68
    eve
    0.65
     Misty
    0.65
    rences
    0.63
    cil
    0.62
     appropriation
    0.61
     foremost
    0.61
    edly
    0.61
     tack
    0.61
    Act Density 0.097%

    No Known Activations