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

    Neuronpedia

    INDEX
    Explanations

    the name "Max" followed by a number indicating approval or significance

    oai_token-act-pair · gpt-3.5-turbo

    the name "Max" in various contexts and mentions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alam
    -0.79
    sbm
    -0.77
    é»Ĵ
    -0.76
    RECT
    -0.75
    taboola
    -0.74
    soType
    -0.73
    ij士
    -0.73
    GROUND
    -0.70
    tale
    -0.70
    wark
    -0.70
    POSITIVE LOGITS
    imus
    1.18
    imil
    1.05
     Max
    1.03
    imize
    0.97
     Payne
    0.94
    Max
    0.90
    imal
    0.86
    itar
    0.81
    ima
    0.77
    imates
    0.76
    Act Density 0.007%

    No Known Activations