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

    Neuronpedia

    INDEX
    Explanations

    words related to cars or vehicles

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and transportation-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANC
    -0.66
    heit
    -0.65
    itely
    -0.65
     tremend
    -0.64
    ulus
    -0.63
    usive
    -0.63
    token
    -0.62
    eanor
    -0.62
     Dru
    -0.61
    closure
    -0.61
    POSITIVE LOGITS
     submarines
    0.81
     headlights
    0.79
     crews
    0.74
     trucks
    0.72
     bicycles
    0.71
    haul
    0.71
     radios
    0.71
     towed
    0.70
     equipped
    0.70
    ouver
    0.69
    Act Density 0.614%

    No Known Activations