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

    Neuronpedia

    INDEX
    Explanations

    words related to maximizing or minimizing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to maximizing and minimizing outcomes or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.80
    ker
    -0.79
    gob
    -0.73
    enegger
    -0.72
    lis
    -0.72
    wall
    -0.70
    lust
    -0.70
    Else
    -0.69
    king
    -0.69
    arter
    -0.67
    POSITIVE LOGITS
    nesota
    0.92
    imize
    0.91
     maximize
    0.90
     maximizing
    0.85
     utilization
    0.81
     minimize
    0.81
     mileage
    0.79
     maxim
    0.79
     minim
    0.78
     amounts
    0.77
    Act Density 0.033%

    No Known Activations