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

    Neuronpedia

    INDEX
    Explanations

    the word "Vice" followed by a title or name

    oai_token-act-pair · gpt-3.5-turbo

    references to vice presidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carnegie
    -0.71
     "$:/
    -0.70
    onite
    -0.69
    ramid
    -0.67
    obyl
    -0.66
    itsch
    -0.66
    astical
    -0.65
    iary
    -0.65
    ebook
    -0.64
    bley
    -0.64
    POSITIVE LOGITS
     versa
    1.08
     Vice
    0.77
    mire
    0.76
    cipled
    0.75
     Counsel
    0.72
    Vice
    0.71
    wave
    0.69
    boss
    0.69
     Marshal
    0.68
    rah
    0.68
    Act Density 0.006%

    No Known Activations