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

    Neuronpedia

    INDEX
    Explanations

    curly braces, indicating a programming or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SOUNDBITE
    -0.67
    neté
    -0.57
    ÁND
    -0.57
    sscanf
    -0.57
     AsyncTask
    -0.54
    orsk
    -0.49
    DTD
    -0.48
     = 
    -0.47
    fscanf
    -0.47
    DispatchToProps
    -0.47
    POSITIVE LOGITS
     {
    0.93
    ++){
    0.89
    {
    0.87
    {
    0.84
    '){
    0.83
    "])){
    0.83
    '])){
    0.82
    ])){
    0.81
    (){
    0.78
    ++){
    0.77
    Act Density 0.197%

    No Known Activations