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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating scheduled events or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate scheduled events or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anon
    -0.74
    Myth
    -0.65
    MO
    -0.64
    tex
    -0.62
    feeding
    -0.62
    Ranked
    -0.62
    kai
    -0.62
     Hardcore
    -0.61
    JV
    -0.61
    culture
    -0.60
    POSITIVE LOGITS
     arrive
    0.80
     expire
    0.74
     sometime
    0.69
    DeliveryDate
    0.68
     retire
    0.68
    oreAnd
    0.67
     pione
    0.67
     deliver
    0.64
     diligence
    0.64
     arra
    0.64
    Act Density 0.043%

    No Known Activations