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

    Neuronpedia

    INDEX
    Explanations

    descriptions of devices or machines being powered by a source or technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of being powered or energized by some source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordan
    -0.81
    esan
    -0.79
    ynski
    -0.69
    esi
    -0.68
    ãģĵ
    -0.67
    alty
    -0.66
    ei
    -0.64
    roma
    -0.62
    eret
    -0.61
     Borders
    -0.61
    POSITIVE LOGITS
     powered
    0.89
    wagen
    0.85
     turbines
    0.83
     Powered
    0.76
    powered
    0.75
     propulsion
    0.74
     powering
    0.74
     locom
    0.74
     generators
    0.73
     propel
    0.73
    Act Density 0.072%

    No Known Activations