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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    adem
    -0.74
    bryce
    -0.67
    hurst
    -0.66
    isco
    -0.66
    bolt
    -0.66
    arro
    -0.63
    pora
    -0.63
    arily
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    vier
    -0.62
    POSITIVE LOGITS
    actionDate
    0.69
    oxin
    0.68
     Addiction
    0.65
     Minutes
    0.65
    ocy
    0.65
     Poverty
    0.64
    VIDIA
    0.64
     Hungry
    0.63
     exhaustion
    0.62
     Lonely
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.