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

    Neuronpedia

    INDEX
    Explanations

    emotions and behaviors related to understanding and relating to others, such as empathy, compassion, and sympathy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ouver
    -0.74
    kj
    -0.74
    bris
    -0.71
    aer
    -0.69
    orn
    -0.68
    heimer
    -0.67
    corn
    -0.65
    jong
    -0.65
    arde
    -0.65
    umbers
    -0.64
    POSITIVE LOGITS
     towards
    0.83
     toward
    0.79
     sympathy
    0.77
     uncond
    0.73
    arity
    0.72
    ISM
    0.72
    ately
    0.71
     reciproc
    0.70
     Towards
    0.70
     pard
    0.67
    Act Density 11.108%

    No Known Activations