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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ma" and variations of the theme of exploitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppuden
    -0.56
     initComponents
    -0.45
     مشين
    -0.45
    rungsseite
    -0.44
     Serikat
    -0.44
    unref
    -0.43
    ChildScrollView
    -0.42
    chartInstance
    -0.42
    Bronnen
    -0.42
    WireFormatLite
    -0.42
    POSITIVE LOGITS
     pun
    0.95
     Pun
    0.89
     exploit
    0.88
    Pun
    0.88
    pun
    0.85
     PUN
    0.84
    ma
    0.83
     lease
    0.72
     penalty
    0.70
     punishment
    0.70
    Act Density 0.310%

    No Known Activations