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

    Neuronpedia

    INDEX
    Explanations

    instances related to electric events or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to electrical energy or electric devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.71
     Mara
    -0.67
    xus
    -0.66
    won
    -0.65
     Mayer
    -0.64
    lust
    -0.63
     UNITED
    -0.62
     awoken
    -0.61
    allery
    -0.60
    amia
    -0.60
    POSITIVE LOGITS
     propulsion
    0.98
     motors
    0.88
     grids
    0.87
     locom
    0.85
    ity
    0.81
     currents
    0.80
     grid
    0.78
    Charge
    0.78
     Powered
    0.77
     powered
    0.76
    Act Density 0.034%

    No Known Activations