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

    Neuronpedia

    INDEX
    Explanations

    words related to reduction or decrease in intensity or amount

    oai_token-act-pair · gpt-3.5-turbo

    words related to processes of reduction or minimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beit
    -0.74
    swick
    -0.66
     Dover
    -0.63
    Spons
    -0.62
     Filip
    -0.62
     Geneva
    -0.61
     Apostle
    -0.60
    mount
    -0.59
     Monstrous
    -0.59
     Emanuel
    -0.59
    POSITIVE LOGITS
    lease
    0.85
     downwards
    0.79
     airflow
    0.78
    angular
    0.76
    xes
    0.75
     coupling
    0.75
     responsiveness
    0.73
    undown
    0.73
    jri
    0.71
     shading
    0.70
    Act Density 0.111%

    No Known Activations