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

    Neuronpedia

    INDEX
    Explanations

    references to motorcycles

    oai_token-act-pair · gpt-3.5-turbo

    references to motorcycles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erion
    -0.81
    ifice
    -0.81
    onne
    -0.80
    ochond
    -0.79
    eele
    -0.77
    mble
    -0.76
    imentary
    -0.76
    urated
    -0.76
    iary
    -0.75
    gage
    -0.75
    POSITIVE LOGITS
     motorcycle
    0.92
     motorcycles
    0.85
    cycles
    0.84
     racing
    0.74
     rider
    0.72
    cycle
    0.71
     gangs
    0.70
     platoon
    0.67
     Samurai
    0.67
     taxi
    0.66
    Act Density 0.018%

    No Known Activations