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

    Neuronpedia

    INDEX
    Explanations

    declarations of classes in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.80
     Shaksp
    -0.67
     useDispatch
    -0.63
     mohair
    -0.62
     Admiralty
    -0.60
     Ceramby
    -0.59
     Cientí
    -0.59
     فريبيس
    -0.59
     Longfellow
    -0.58
     Viceroy
    -0.58
    POSITIVE LOGITS
    帖最后由
    0.76
     class
    0.68
    Parcelize
    0.64
    $")
    0.63
    class
    0.61
    "){
    0.60
    '){
    0.58
    _'.$
    0.58
    tagext
    0.57
    ?}",
    0.57
    Act Density 0.071%

    No Known Activations