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

    Neuronpedia

    INDEX
    Explanations

    addresses, locations, or directions involving "Drive"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Drive," possibly indicating locations or directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -1.05
    icipated
    -0.85
    ileaks
    -0.78
    iannopoulos
    -0.74
    krit
    -0.72
    ANN
    -0.70
    wealth
    -0.69
     constitu
    -0.68
    ambo
    -0.67
    abad
    -0.66
    POSITIVE LOGITS
    train
    0.87
    away
    0.82
    bys
    0.78
     drives
    0.77
    Drive
    0.75
    wheel
    0.73
    bike
    0.72
     thru
    0.71
    driving
    0.71
     drive
    0.70
    Act Density 0.023%

    No Known Activations