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

    Neuronpedia

    INDEX
    Explanations

    numerical data or values associated with specific attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pexpr
    -0.57
     وتسجيلات
    -0.54
     earnings
    -0.53
    wari
    -0.51
    ize
    -0.49
    ))[
    -0.49
     Earnings
    -0.48
     ос
    -0.48
    lair
    -0.48
     var
    -0.47
    POSITIVE LOGITS
     noires
    0.80
     nicio
    0.78
     industriels
    0.77
     habet
    0.76
     barbati
    0.73
     religieuses
    0.73
     marquées
    0.72
     violenza
    0.71
     Monfieur
    0.70
     perfons
    0.69
    Act Density 0.565%

    No Known Activations