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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unique characteristics or attributes of different elements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe distinct entities or items, each having their own unique attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qus
    -0.69
    tics
    -0.68
    soDeliveryDate
    -0.67
     angered
    -0.67
    Alert
    -0.67
    haven
    -0.66
    Wolf
    -0.66
    didn
    -0.65
    metal
    -0.65
    rers
    -0.64
    POSITIVE LOGITS
     individually
    1.28
     separately
    1.03
     unique
    0.88
     respective
    0.87
     independently
    0.85
     imaginable
    0.85
     distinct
    0.85
     individual
    0.81
     uniquely
    0.80
     successive
    0.79
    Act Density 0.314%

    No Known Activations