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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating events or actions that happened in the past before some specific time or event

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "long before" and its variations, indicating a discussion of time and events in relation to the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gallery
    -0.88
    ©¶æ
    -0.73
    án
    -0.71
    que
    -0.70
    MO
    -0.69
    MN
    -0.67
    aq
    -0.65
    MI
    -0.64
    PLA
    -0.64
    MAC
    -0.63
    POSITIVE LOGITS
     adulthood
    0.78
     forgotten
    0.75
    agos
    0.67
     discarded
    0.67
    ounters
    0.67
    essors
    0.65
    ustomed
    0.65
    inctions
    0.62
     (>
    0.62
     disillusion
    0.61
    Act Density 0.064%

    No Known Activations