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

    Neuronpedia

    INDEX
    Explanations

    patterns in code structure, specifically focusing on blocks defined by curly braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vidite
    -0.92
     للمعارف
    -0.76
    antMatchers
    -0.68
    Попис
    -0.64
     AsyncTask
    -0.64
    mtrl
    -0.63
    canestro
    -0.61
    াঁ
    -0.61
    Sik
    -0.59
     Smyrna
    -0.59
    POSITIVE LOGITS
    __':
    1.16
    __":
    1.07
    __":
    1.03
    __':
    0.98
    --){
    0.94
    SequentialGroup
    0.88
    "])){
    0.86
    Wasn
    0.85
     الحره
    0.82
    ))){
    0.81
    Act Density 0.043%

    No Known Activations