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

    Neuronpedia

    INDEX
    Explanations

    structured code elements, particularly in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ه
    -0.88
    e
    -0.84
     Amos
    -0.71
     Faber
    -0.71
     estimés
    -0.69
     Aufs
    -0.69
    ed
    -0.69
     pary
    -0.68
    koda
    -0.68
    Amos
    -0.67
    POSITIVE LOGITS
     {
    1.80
    ({
    1.58
    '){
    1.58
    ()){
    1.53
    "){
    1.50
    ]){
    1.49
    ++){
    1.48
    '])){
    1.48
    )){
    1.48
    "):
    1.46
    Act Density 0.030%

    No Known Activations