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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of the soul

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.72
    httphttps
    -0.72
     themſelves
    -0.70
     Versailles
    -0.69
     terrorism
    -0.67
     Monfieur
    -0.67
     Maharaja
    -0.65
    ppled
    -0.65
     mercantile
    -0.65
     Pears
    -0.64
    POSITIVE LOGITS
     soul
    3.29
     Soul
    2.98
    soul
    2.96
    Soul
    2.79
     SOUL
    2.69
     souls
    2.64
     Souls
    2.31
    Souls
    2.16
     âme
    1.77
    魂
    1.69
    Act Density 0.038%

    No Known Activations