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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their feelings or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.94
     NSCoder
    -0.81
    DoubleQuotes
    -0.79
     calendriers
    -0.76
    awakeFromNib
    -0.72
    "}")
    -0.71
    ]")]
    -0.69
    
    -0.69
    =$?
    -0.67
     समीक्षक
    -0.67
    POSITIVE LOGITS
     ведь
    0.54
     e
    0.52
     literally
    0.50
     so
    0.50
    he
    0.49
     i
    0.49
    even
    0.48
     even
    0.48
     I
    0.48
     just
    0.48
    Act Density 0.224%

    No Known Activations