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

    Neuronpedia

    INDEX
    Explanations

    indicators of data quality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.90
     myſelf
    -0.88
     Мексичка
    -0.84
     Theſe
    -0.83
    ItemBackground
    -0.81
     تضيفلها
    -0.78
    RenderAtEndOf
    -0.77
     otomatig
    -0.77
     itſelf
    -0.76
     ExecuteAsync
    -0.75
    POSITIVE LOGITS
    till
    0.55
    ante
    0.52
    <eos>
    0.49
    tel
    0.49
    til
    0.49
    неса
    0.48
    ﾉ
    0.47
     tussen
    0.47
     instead
    0.47
     inter
    0.47
    Act Density 0.356%

    No Known Activations