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

    Neuronpedia

    INDEX
    Explanations

    the number "two" or "three" that appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of quantities, particularly the numbers two and three

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obin
    -0.78
    vention
    -0.76
    urgy
    -0.72
    biology
    -0.71
     [&
    -0.71
    Temperature
    -0.69
    urden
    -0.69
    agame
    -0.67
    heter
    -0.67
    ãĤ´ãĥ³
    -0.64
    POSITIVE LOGITS
    teen
    1.06
    teenth
    1.05
     dozen
    0.98
     successive
    0.93
     consecutive
    0.93
     hundred
    0.91
     unidentified
    0.87
     unnamed
    0.86
     months
    0.86
     weeks
    0.83
    Act Density 0.173%

    No Known Activations