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

    Neuronpedia

    INDEX
    Explanations

    terms related to conditionality and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.15
     mixer
    -0.15
    ilan
    -0.14
    _BS
    -0.13
     Merk
    -0.13
    ãģĿãģĨãģª
    -0.13
    ibs
    -0.13
    -ser
    -0.13
    agan
    -0.13
    ìŀij
    -0.13
    POSITIVE LOGITS
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.20
    ä¹İ
    0.15
    ÚĺÙĩ
    0.15
    ált
    0.15
    ologically
    0.14
    eon
    0.14
    ecz
    0.14
    uito
    0.14
    vore
    0.14
    δή
    0.14
    Act Density 0.160%

    No Known Activations