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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated parameters or settings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     lụ
    -0.55
     dob
    -0.50
    -/
    -0.47
    /.
    -0.45
     McGu
    -0.45
    ante
    -0.45
     tụ
    -0.45
    zieh
    -0.45
    atov
    -0.43
    בר
    -0.43
    POSITIVE LOGITS
     esternos
    0.73
    🏻‍♀️
    0.71
     Efq
    0.64
     الرياضيه
    0.64
    তথ্যসূত্র
    0.62
     otomatig
    0.61
     itſelf
    0.61
    imwrite
    0.60
    ьаж
    0.60
    jspb
    0.60
    Act Density 0.015%

    No Known Activations