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

    Neuronpedia

    INDEX
    Explanations

    references to 'cup' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grasshopper
    -0.58
    GetAxis
    -0.57
    UnsafeEnabled
    -0.55
     Pris
    -0.55
    ('*',
    -0.53
     Bourgoin
    -0.53
     Krie
    -0.53
     Kepler
    -0.50
    HasKey
    -0.49
     Geburtstag
    -0.49
    POSITIVE LOGITS
     cup
    0.93
     Cups
    0.80
     Cup
    0.79
     sw
    0.78
    HtmlAttribute
    0.75
     cu
    0.74
    NOPQRST
    0.74
     cups
    0.74
    ffilm
    0.71
    cup
    0.68
    Act Density 0.176%

    No Known Activations