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

    Neuronpedia

    INDEX
    Explanations

    references to railroads and transportation infrastructure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Libre
    -0.72
     Ambrose
    -0.69
     Homo
    -0.67
     Parenthood
    -0.63
     Izan
    -0.62
     blo
    -0.62
     Hague
    -0.62
     Naomi
    -0.61
     Duchess
    -0.61
    Gene
    -0.61
    POSITIVE LOGITS
    roads
    1.72
    road
    1.09
    craft
    1.09
    ways
    1.08
    cars
    1.06
    plane
    0.89
    ings
    0.89
    ulic
    0.86
    service
    0.85
     Transit
    0.85
    Act Density 0.012%

    No Known Activations