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

    Neuronpedia

    INDEX
    Explanations

    references to taxi services and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to taxi services and related operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -1.03
    utz
    -0.78
    wart
    -0.75
    isite
    -0.75
    natureconservancy
    -0.75
    mberg
    -0.72
    reditary
    -0.71
    vironment
    -0.69
     Forge
    -0.68
    itud
    -0.67
    POSITIVE LOGITS
     taxi
    0.97
     cab
    0.94
     taxis
    0.89
     rides
    0.81
     drivers
    0.81
     courier
    0.76
    LOS
    0.74
    bay
    0.74
     ride
    0.74
    driver
    0.74
    Act Density 0.014%

    No Known Activations