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

    Neuronpedia

    INDEX
    Explanations

    numbers representing age or numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to quantities or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.86
    amaru
    -0.72
    urus
    -0.67
    gradient
    -0.63
     guid
    -0.62
    imaru
    -0.62
     parity
    -0.62
    agame
    -0.61
    folk
    -0.60
    atum
    -0.60
    POSITIVE LOGITS
    th
    1.00
    00
    0.99
     Deg
    0.93
    rd
    0.93
    %"
    0.91
     percent
    0.89
     Minutes
    0.87
    º
    0.87
    %
    0.87
    nd
    0.87
    Act Density 0.176%

    No Known Activations