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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fundamental concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to foundational concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cape
    -0.78
    soDeliveryDate
    -0.73
    hov
    -0.69
    enium
    -0.68
    pher
    -0.68
    stra
    -0.67
    vision
    -0.66
    cap
    -0.66
    isSpecialOrderable
    -0.64
    halla
    -0.64
    POSITIVE LOGITS
    ALLY
    1.02
    ially
    0.94
    ALS
    0.92
    als
    0.90
    ional
    0.83
    IAL
    0.83
    ally
    0.78
    ale
    0.75
    iary
    0.74
    alled
    0.72
    Act Density 0.137%

    No Known Activations