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

    Neuronpedia

    INDEX
    Explanations

    dates in Oct 2014

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oreAnd
    -0.74
     Palestin
    -0.72
     unnecess
    -0.72
     Brill
    -0.72
    anked
    -0.71
     ensu
    -0.70
     HUN
    -0.70
    zbollah
    -0.68
    DeliveryDate
    -0.67
    timer
    -0.67
    POSITIVE LOGITS
    od
    0.76
    type
    0.68
    x
    0.68
     type
    0.67
    op
    0.66
     ele
    0.66
    ex
    0.66
    01
    0.64
    wcsstore
    0.64
    object
    0.63
    Act Density 0.226%

    No Known Activations