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

    Neuronpedia

    INDEX
    Explanations

    dates written in numeral form

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.67
    ably
    -0.61
    ikawa
    -0.61
    imaru
    -0.61
    ulsion
    -0.58
    withstanding
    -0.58
    theless
    -0.57
     Paste
    -0.57
    acco
    -0.56
    ensibly
    -0.56
    POSITIVE LOGITS
    th
    1.56
    teenth
    1.01
    venth
    0.98
    rd
    0.97
    hest
    0.94
    TH
    0.93
    ieth
    0.92
    nd
    0.85
     th
    0.85
     acre
    0.83
    Act Density 0.099%

    No Known Activations