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

    Neuronpedia

    INDEX
    Explanations

    specific street names and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.78
    merce
    -0.77
    arian
    -0.76
    emort
    -0.75
    eer
    -0.74
    arians
    -0.70
    onom
    -0.69
    ividual
    -0.68
    cause
    -0.68
    eness
    -0.68
    POSITIVE LOGITS
     Station
    0.93
     NW
    0.92
     Crossing
    0.83
     Corridor
    0.82
     Tunnel
    0.82
     Plaza
    0.82
     corridor
    0.82
     intersection
    0.81
     Armory
    0.79
     Bridge
    0.78
    Act Density 0.019%

    No Known Activations