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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions related to configuring settings

    oai_token-act-pair · gpt-3.5-turbo

    commands related to configuration or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    past
    -0.65
     Vaugh
    -0.64
    geoning
    -0.62
     Sacrifice
    -0.62
    article
    -0.61
    lance
    -0.61
    earth
    -0.61
    alez
    -0.60
     Indies
    -0.59
     tears
    -0.59
    POSITIVE LOGITS
     aside
    1.06
    tle
    1.06
    Timeout
    0.97
    upt
    0.90
     defaults
    0.89
    uid
    0.88
     parameters
    0.87
     reminders
    0.86
    ter
    0.83
     thresholds
    0.81
    Act Density 0.052%

    No Known Activations