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

    Neuronpedia

    INDEX
    Explanations

    terms related to taxi services and drivers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Гер
    -0.53
    ouwen
    -0.51
     Hou
    -0.50
    perd
    -0.50
    Hou
    -0.49
    forest
    -0.49
     drums
    -0.49
     iman
    -0.48
     nature
    -0.48
     Nature
    -0.47
    POSITIVE LOGITS
     Taxi
    1.53
     taxi
    1.52
    Taxi
    1.42
    taxi
    1.38
     taxis
    1.35
     cabs
    1.18
     cab
    1.09
    Cab
    0.93
     такси
    0.93
    Uber
    0.87
    Act Density 0.005%

    No Known Activations