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

    Neuronpedia

    INDEX
    Explanations

    the word "Masters" at different levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to "Masters" as a key theme or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.74
     Subway
    -0.66
    LIN
    -0.66
     Gregg
    -0.65
    ality
    -0.64
     Hancock
    -0.63
    ãĤ¡
    -0.62
     Ferr
    -0.62
     Spencer
    -0.62
    itial
    -0.62
    POSITIVE LOGITS
    hips
    0.86
    pace
    0.85
    pread
    0.83
    hift
    0.83
    peed
    0.83
    chool
    0.80
    manship
    0.80
    ammy
    0.79
    hirt
    0.79
    xual
    0.77
    Act Density 0.019%

    No Known Activations