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

    Neuronpedia

    INDEX
    Explanations

    themes of love, charity, and compassion in discussions about moral values

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

    associated with positive emotions

    np_acts-logits-general · gemini-2.0-flash

    love and forgiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flops
    -0.50
    culada
    -0.46
    IntoConstraints
    -0.46
     restlessness
    -0.46
    存于互联网档案馆
    -0.46
    iedział
    -0.46
     siphon
    -0.44
    teenth
    -0.44
     stealth
    -0.44
     fidget
    -0.44
    POSITIVE LOGITS
     kindness
    0.90
     Kindness
    0.88
     compassion
    0.79
     Compassion
    0.79
    Compassion
    0.79
     Forgiveness
    0.75
     peace
    0.74
     hate
    0.73
     humanity
    0.73
     kinder
    0.71
    Act Density 0.207%

    No Known Activations