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

    Neuronpedia

    INDEX
    Explanations

    phrases related to how something works or operates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to functioning or operational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.81
    livion
    -0.71
    asio
    -0.68
    arters
    -0.64
    gard
    -0.64
    gur
    -0.63
    ousing
    -0.63
    osi
    -0.63
    ndra
    -0.62
    ike
    -0.62
    POSITIVE LOGITS
     differs
    0.81
     Different
    0.76
     versus
    0.76
     differently
    0.76
     geographically
    0.75
     interact
    0.71
     compared
    0.68
     contrasted
    0.67
     differ
    0.67
     today
    0.67
    Act Density 0.197%

    No Known Activations