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

    soul's state or belonging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Garry
    -0.50
     كومونز
    -0.50
     للمعارف
    -0.49
    ickers
    -0.47
     Grüsse
    -0.47
     Janvier
    -0.47
     Marten
    -0.46
     bleue
    -0.45
     Utilizamos
    -0.44
    錦
    -0.44
    POSITIVE LOGITS
     soul
    2.05
    Soul
    1.91
     Soul
    1.88
    soul
    1.81
     SOUL
    1.70
     souls
    1.51
     Souls
    1.35
    Souls
    1.24
     âmes
    1.13
    灵魂
    1.07
    Act Density 0.003%

    No Known Activations