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

    Neuronpedia

    INDEX
    Explanations

    occurrences of opening and closing curly braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oporosis
    -0.86
    ing
    -0.73
    rsquo
    -0.71
    nbsp
    -0.67
    όρ
    -0.65
     textStatus
    -0.64
    Cual
    -0.64
    gwick
    -0.64
     Harg
    -0.64
     doubtnut
    -0.64
    POSITIVE LOGITS
     {
    1.48
     {
    1.26
     ***!
    1.07
     {\
    1.07
    __(/*!
    1.02
    |}{
    0.98
     {(
    0.92
    améli
    0.88
     {
    0.87
     nahilalakip
    0.86
    Act Density 0.195%

    No Known Activations