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

    Neuronpedia

    INDEX
    Explanations

    references to fill colors in graphical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.65
    addObject
    -0.65
    Kaieteur
    -0.61
     Occasion
    -0.61
    yttä
    -0.61
    vägen
    -0.60
    subcategory
    -0.59
    flüs
    -0.59
     Wikimedijinoj
    -0.59
    gestone
    -0.57
    POSITIVE LOGITS
    fill
    2.22
    Fill
    1.81
     Fill
    1.70
     fill
    1.54
    FILL
    1.53
     FILL
    1.42
    fills
    1.37
     fills
    1.08
     Fillmore
    0.93
    filling
    0.92
    Act Density 0.063%

    No Known Activations