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

    Neuronpedia

    INDEX
    Explanations

    references to healthy eating habits or behaviors

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

    healthy eating patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.64
     فريبيس
    -0.62
     CURIAM
    -0.57
    zeß
    -0.54
    yszer
    -0.53
    roep
    -0.49
    ソッド
    -0.49
     almofada
    -0.49
    นะครับ
    -0.49
     humanidade
    -0.48
    POSITIVE LOGITS
     Eating
    1.69
     eating
    1.66
    Eating
    1.66
    eating
    1.53
    dining
    0.94
     dining
    0.85
     eaters
    0.85
    drinking
    0.82
     eater
    0.79
     comiendo
    0.79
    Act Density 0.004%

    No Known Activations