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

    Neuronpedia

    INDEX
    Explanations

    terms related to rights, obligations, and principles in legal or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \
    -0.54
    '
    -0.48
     =
    -0.48
    =
    -0.47
     
    -0.44
     "
    -0.44
     is
    -0.42
    aster
    -0.41
      
    -0.41
    ou
    -0.40
    POSITIVE LOGITS
     متعلقه
    1.08
    AutoresizingMask
    0.89
    SharedCtor
    0.88
    ViewInit
    0.85
    دانشنامهٔ
    0.84
    الحياه
    0.82
     للاسماء
    0.80
    ValueStyle
    0.80
    enseignements
    0.79
     محفوظة
    0.78
    Act Density 0.528%

    No Known Activations