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

    Neuronpedia

    INDEX
    Explanations

    terms related to roads, lanes, or gears in vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ([^
    -0.83
    ristmas
    -0.75
     AssemblyProduct
    -0.70
    戮
    -0.68
     helse
    -0.67
     Broken
    -0.67
     mør
    -0.66
     randon
    -0.65
    Beau
    -0.65
    ürk
    -0.65
    POSITIVE LOGITS
    IsContent
    0.92
     lane
    0.83
     LANE
    0.79
     WARD
    0.79
     lanes
    0.79
    styleType
    0.77
     Lane
    0.76
     rack
    0.74
     Rack
    0.73
    LANE
    0.72
    Act Density 0.181%

    No Known Activations