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

    Neuronpedia

    INDEX
    Explanations

    accidents involving crashes

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving crashes and collisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertain
    -0.75
    glers
    -0.74
     persuasion
    -0.74
    abled
    -0.73
    assadors
    -0.71
    esse
    -0.71
    VPN
    -0.69
    otle
    -0.68
    inct
    -0.68
    00200000
    -0.67
    POSITIVE LOGITS
     collision
    1.02
     takeoff
    1.00
     debris
    0.98
     injuring
    0.97
     cliff
    0.94
     landing
    0.92
     brakes
    0.88
     collided
    0.87
     crash
    0.87
     prope
    0.85
    Act Density 0.337%

    No Known Activations