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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their varied usages in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.61
    それとも
    -0.59
    性和
    -0.56
     or
    -0.55
     vícti
    -0.54
     prisonniers
    -0.53
     genoux
    -0.52
     или
    -0.52
    이나
    -0.51
    Literatuur
    -0.50
    POSITIVE LOGITS
     alike
    0.77
     تضيفلها
    0.74
     linkovi
    0.70
    NewGuid
    0.69
     оригіналу
    0.64
    AutoScale
    0.64
     المعيارى
    0.64
     CWE
    0.61
    (!__
    0.61
     समीक्षक
    0.60
    Act Density 0.691%

    No Known Activations