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

    Neuronpedia

    INDEX
    Explanations

    words related to alerts or notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mawr
    -0.83
    -0.76
     aDecoder
    -0.76
    windowFixed
    -0.75
    tvguidetime
    -0.73
    RegressionTest
    -0.71
    valho
    -0.70
    uría
    -0.70
     незавершена
    -0.70
     getM
    -0.69
    POSITIVE LOGITS
     alert
    1.77
     alerts
    1.77
     Alert
    1.70
     Alerts
    1.64
     ALERT
    1.52
    Alerts
    1.52
    Alert
    1.48
    ALERT
    1.48
    alert
    1.42
    alerts
    1.42
    Act Density 0.004%

    No Known Activations