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

    Neuronpedia

    INDEX
    Explanations

    references to compassion and compassionate behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    compassion and related virtues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Voulez
    -0.39
     happenings
    -0.39
     Whig
    -0.38
     Gefahr
    -0.37
     trivi
    -0.37
     alre
    -0.36
     Whigs
    -0.35
     procès
    -0.35
     trivia
    -0.34
     hitting
    -0.34
    POSITIVE LOGITS
     Compassion
    1.95
     compassion
    1.91
     compassionate
    1.88
    Compassion
    1.88
     compas
    1.32
    assion
    1.30
     empathetic
    0.91
     empathy
    0.82
    Passion
    0.79
     caring
    0.78
    Act Density 0.002%

    No Known Activations