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

    Neuronpedia

    INDEX
    Explanations

    evaluative language indicating significance or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     di
    -0.46
    slidesToShow
    -0.45
    <eos>
    -0.42
    !
    -0.38
     katanya
    -0.37
     Lombardo
    -0.37
     légales
    -0.36
    الیا
    -0.36
    derabad
    -0.35
    :
    -0.35
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
     utafitiHapana
    0.93
    醐
    0.92
    ScopeManager
    0.88
    WithIOException
    0.87
     purest
    0.86
    Hentet
    0.84
     OFDb
    0.81
     truest
    0.81
    rawDesc
    0.81
    Act Density 0.154%

    No Known Activations