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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values and related formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.53
    Бахар
    -0.48
     enfans
    -0.47
    roek
    -0.46
     miễn
    -0.46
    david
    -0.46
    Benzene
    -0.44
    لمين
    -0.44
     autorytatywna
    -0.43
     kembali
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.74
     Мексичка
    0.67
    awtextra
    0.66
     समीक्षाओं
    0.65
    addCriterion
    0.64
    انگلیسی
    0.63
    RetentionPolicy
    0.63
    titleMargin
    0.60
     intptr
    0.59
     ComVisible
    0.58
    Act Density 0.760%

    No Known Activations