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

    Neuronpedia

    INDEX
    Explanations

    mentions of motorcycles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of motorcycles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilib
    -0.81
     Wallace
    -0.73
    Wall
    -0.69
     Kell
    -0.68
    Ell
    -0.67
     Delicious
    -0.66
     Iv
    -0.65
    uv
    -0.64
    riched
    -0.64
    ald
    -0.63
    POSITIVE LOGITS
     motorcycle
    3.56
     motorcycles
    3.05
     bike
    2.04
     bicycle
    1.87
    bike
    1.85
     bikes
    1.75
     Motor
    1.70
    Motor
    1.67
     automobile
    1.65
     Harley
    1.65
    Act Density 0.017%

    No Known Activations