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

    Neuronpedia

    INDEX
    Explanations

    quotes or dialogue in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    الحياه
    -0.99
    Архівовано
    -0.76
     الرياضيه
    -0.71
    __.__
    -0.66
    gyz
    -0.65
    页面存档备份
    -0.61
     Mep
    -0.60
    Datuak
    -0.59
    BackStack
    -0.58
     beginnetje
    -0.57
    POSITIVE LOGITS
     ""
    0.66
    /"
    0.66
     -"
    0.63
    ."
    0.63
     '"
    0.61
    ?"
    0.61
     "'
    0.60
     Arias
    0.58
     :"
    0.58
    ..."
    0.57
    Act Density 0.077%

    No Known Activations