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

    Neuronpedia

    INDEX
    Explanations

    terms indicating a high level of quality or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.80
    0
    -0.75
    tableFuture
    -0.69
     BoxDecoration
    -0.67
    onel
    -0.64
     prie
    -0.62
    <b>
    -0.62
     Вікіпе
    -0.60
    ubation
    -0.60
    al
    -0.60
    POSITIVE LOGITS
    ientras
    0.92
     متحده
    0.91
    angliski
    0.90
    highly
    0.89
    liminary
    0.88
    {}",
    0.85
    Highly
    0.84
    %"),
    0.84
     muſt
    0.83
    )"),
    0.82
    Act Density 0.091%

    No Known Activations