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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation and whitespace patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     naselje
    -0.49
     publiek
    -0.48
    Rüyada
    -0.45
     novidades
    -0.44
     popolari
    -0.43
     Ankunft
    -0.43
     $(".
    -0.43
    <bos>
    -0.42
     Cohn
    -0.42
     campana
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.98
     autorytatywna
    0.93
     Roskov
    0.88
     صوتيه
    0.86
    RenderAtEndOf
    0.83
    0.82
     propOrder
    0.81
    FormTagHelper
    0.80
    viewDidLoad
    0.79
    ftagPool
    0.78
    Act Density 0.389%

    No Known Activations