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

    Neuronpedia

    INDEX
    Explanations

    mentions of events or activities related to marathons

    oai_token-act-pair · gpt-3.5-turbo

    references to marathons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suscept
    -0.77
    metics
    -0.75
    orum
    -0.73
    ortium
    -0.69
    oshop
    -0.68
    gypt
    -0.68
    choes
    -0.67
     Debor
    -0.67
    olia
    -0.67
    unin
    -0.65
    POSITIVE LOGITS
     runner
    1.05
     Runner
    0.96
     runners
    0.93
     marathon
    0.88
    athon
    0.80
     Marathon
    0.79
     Polo
    0.75
     bombing
    0.73
    NING
    0.72
     bombings
    0.69
    Act Density 0.024%

    No Known Activations