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

    Neuronpedia

    INDEX
    Explanations

    references to food portions and their sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     portions
    -0.90
     portion
    -0.89
    portion
    -0.70
    Portion
    -0.66
     Portion
    -0.60
     Portions
    -0.59
     porción
    -0.49
    ambilan
    -0.41
     kısm
    -0.39
    partie
    -0.38
    POSITIVE LOGITS
     kaarangay
    0.61
    ativement
    0.54
     Мексичка
    0.54
    Cyfarwyddwr
    0.52
    addContainerGap
    0.52
    RectangleBorder
    0.49
    verifyException
    0.48
     مشين
    0.47
    RuleContext
    0.45
     typelib
    0.45
    Act Density 0.001%

    No Known Activations