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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power plants

    oai_token-act-pair · gpt-3.5-turbo

    terms related to power generation and energy production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.77
    ĸļ
    -0.76
     Von
    -0.73
    glers
    -0.71
    erella
    -0.71
    yrinth
    -0.69
    auder
    -0.67
    odox
    -0.66
     Neurolog
    -0.65
     Immun
    -0.64
    POSITIVE LOGITS
    houses
    1.17
     stations
    1.09
    plant
    1.02
     plants
    1.00
     outage
    0.98
    train
    0.95
     generators
    0.94
     grids
    0.93
    station
    0.93
     Plants
    0.91
    Act Density 0.049%

    No Known Activations