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

    Neuronpedia

    INDEX
    Explanations

    terms related to motors and engines

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of motors and motorsports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.77
     Plain
    -0.76
     Coverage
    -0.72
     Marathon
    -0.70
     Faces
    -0.70
     Penguin
    -0.70
     Hancock
    -0.67
     Hawaiian
    -0.64
     Domain
    -0.63
     Desmond
    -0.63
    POSITIVE LOGITS
    ports
    1.25
    pring
    1.05
    paces
    0.95
    pace
    0.93
    mith
    0.93
    hops
    0.90
    port
    0.88
    hips
    0.86
    manship
    0.85
    wana
    0.83
    Act Density 0.017%

    No Known Activations