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

    Neuronpedia

    INDEX
    Explanations

    programming code syntax and specific symbols

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     breaching
    -0.60
     Nare
    -0.57
     McKay
    -0.53
     procurement
    -0.51
    jri
    -0.51
     Hust
    -0.51
     judging
    -0.50
     Olympia
    -0.50
     catering
    -0.50
     CDs
    -0.50
    POSITIVE LOGITS
    {
    1.00
    array
    0.99
    func
    0.97
    function
    0.96
    Array
    0.96
     {
    0.94
    [[
    0.94
    String
    0.92
    expr
    0.91
    operator
    0.91
    Act Density 0.207%

    No Known Activations