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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.72
     مشين
    -0.62
    MLLoader
    -0.61
    клопе
    -0.58
    SharedDtor
    -0.57
    úsqueda
    -0.57
     Lyra
    -0.57
     viewDidLoad
    -0.55
    itosti
    -0.55
     ""],
    -0.54
    POSITIVE LOGITS
     thanks
    1.27
     grâce
    1.23
    Благодаря
    1.23
     graças
    1.22
     Grâce
    1.19
    ďaka
    1.17
     благодаря
    1.16
     grazie
    1.15
     Dzięki
    1.14
     dzięki
    1.14
    Act Density 0.125%

    No Known Activations