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

    Neuronpedia

    INDEX
    Explanations

    numerical data, particularly relating to dates and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koran
    -0.91
     pleaſure
    -0.87
     myſelf
    -0.85
    ՚
    -0.84
    expandindo
    -0.82
    neſs
    -0.82
    ſelves
    -0.81
     CCR
    -0.79
     Malabar
    -0.78
    ſelf
    -0.78
    POSITIVE LOGITS
     २०
    0.84
     ২০
    0.78
     ۲۰
    0.71
     ۱۹
    0.68
    ۲۰
    0.62
    zarchiwizowane
    0.54
     ";
    0.54
     plages
    0.53
    Portale
    0.53
     past
    0.53
    Act Density 0.875%

    No Known Activations