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

    Neuronpedia

    INDEX
    Explanations

    mentions of the city "Paris" - specifically with variations in spelling

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific location or person related to the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ho
    -0.65
     handle
    -0.65
     sto
    -0.64
     machine
    -0.64
     weight
    -0.63
     div
    -0.62
     household
    -0.61
     Name
    -0.61
     medd
    -0.60
     device
    -0.60
    POSITIVE LOGITS
    aris
    4.74
    arus
    1.52
    aria
    1.43
    ari
    1.34
    aran
    1.32
    arius
    1.28
    atos
    1.28
    agos
    1.27
    oris
    1.18
    arios
    1.10
    Act Density 0.011%

    No Known Activations