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

    Neuronpedia

    INDEX
    Explanations

    references to judgment and control within a societal or hierarchical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fubject
    -0.64
     pleaſure
    -0.60
     myſelf
    -0.59
    HtmlAttribute
    -0.59
     Monfieur
    -0.59
    wnież
    -0.56
     ſta
    -0.54
     للاسماء
    -0.54
    周泽
    -0.54
    TextWatcher
    -0.54
    POSITIVE LOGITS
     shameless
    0.48
     dog
    0.43
     slapped
    0.41
     pit
    0.40
     beaten
    0.40
     shit
    0.39
     outrageous
    0.38
     miserably
    0.38
     Dog
    0.38
     shits
    0.37
    Act Density 0.082%

    No Known Activations