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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lok
    -0.15
    sko
    -0.14
    hou
    -0.14
    GNUC
    -0.14
     ment
    -0.14
    ounce
    -0.14
    _ros
    -0.14
    essler
    -0.14
    анÑĤи
    -0.14
     Jackets
    -0.13
    POSITIVE LOGITS
    undy
    0.17
    ecz
    0.15
    -Ta
    0.14
    awaii
    0.14
    Ä±ÅŁÄ±k
    0.14
    _Metadata
    0.14
     Bonus
    0.14
    bonus
    0.14
    xfff
    0.14
    ukan
    0.13
    Act Density 0.175%

    No Known Activations