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

    Neuronpedia

    INDEX
    Explanations

    references to trucks and related vehicle terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dona
    -0.87
     آم
    -0.75
     emis
    -0.74
     Dona
    -0.71
    ivel
    -0.71
     Naga
    -0.70
     relati
    -0.70
     scales
    -0.70
     Henn
    -0.69
     sovereigns
    -0.69
    POSITIVE LOGITS
     trucks
    1.06
     Trucks
    1.05
     Truck
    0.95
     CONCERT
    0.95
    trucks
    0.94
    Truck
    0.94
     truck
    0.94
     TRUCK
    0.94
     Concert
    0.88
    ruck
    0.79
    Act Density 0.080%

    No Known Activations