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

    Neuronpedia

    INDEX
    Explanations

    points of emphasis or focus in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -1.01
     numberOfRows
    -0.95
    ^(@)
    -0.93
    createCanvas
    -0.92
    orianCalendar
    -0.90
     Chwiliwch
    -0.89
     ComVisible
    -0.87
    +#+#
    -0.86
     GenerationType
    -0.85
     Мексичка
    -0.85
    POSITIVE LOGITS
    _
    0.46
    ↵↵
    0.43
    (
    0.42
     available
    0.42
     delights
    0.41
    to
    0.40
    cin
    0.40
     wonder
    0.40
    cr
    0.39
     featuring
    0.39
    Act Density 0.287%

    No Known Activations