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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '>
    -0.70
    stood
    -0.69
    Sax
    -0.68
     compe
    -0.67
    BIL
    -0.66
     opin
    -0.66
    matter
    -0.65
    ?]
    -0.65
    gio
    -0.62
     afore
    -0.62
    POSITIVE LOGITS
     $
    0.76
    éĹĺ
    0.73
     EntityItem
    0.67
    ults
    0.65
    adiq
    0.64
    displayText
    0.64
     respectively
    0.64
    iPhone
    0.63
     ¥
    0.62
    maximum
    0.62
    Act Density 0.008%

    No Known Activations