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

    Neuronpedia

    INDEX
    Explanations

    mentions of bike races

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive events involving vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tymology
    -0.79
    iar
    -0.78
    berra
    -0.77
    olia
    -0.77
    etheless
    -0.75
     defic
    -0.74
    endiary
    -0.74
    lishes
    -0.73
    osis
    -0.73
    erva
    -0.71
    POSITIVE LOGITS
    horse
    1.18
    course
    1.08
    bike
    1.01
    car
    0.97
    cars
    0.91
     race
    0.79
    Race
    0.76
    nell
    0.76
    hide
    0.76
    boat
    0.76
    Act Density 0.021%

    No Known Activations