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

    Neuronpedia

    INDEX
    Explanations

    JavaScript function definitions and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.90
    laus
    -0.79
    peg
    -0.66
    jong
    -0.65
    endon
    -0.65
     Sins
    -0.65
    vae
    -0.63
    creen
    -0.62
    rium
    -0.62
    born
    -0.62
    POSITIVE LOGITS
    (){
    1.06
     __
    0.81
    ()
    0.81
     ()
    0.80
    func
    0.70
    atic
    0.68
     func
    0.68
    (_
    0.68
    alities
    0.67
    ality
    0.67
    Act Density 0.005%

    No Known Activations