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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to cultural references or national identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÑĢанÑĮ
    -0.24
     вÑĥли
    -0.22
     звиÑĩай
    -0.19
     клÑĥ
    -0.19
     еÑģÑĤе
    -0.18
     ÑĤва
    -0.18
     кÑĥлÑĮÑĤÑĥ
    -0.17
    наÑģлÑĸд
    -0.16
     огÑĢа
    -0.16
     зави
    -0.16
    POSITIVE LOGITS
     Rad
    0.20
     ÐŁÑĢез
    0.20
    org
    0.19
     RAD
    0.19
    деÑĢж
    0.19
     rad
    0.19
     organ
    0.18
    Rad
    0.17
    rada
    0.17
    _rad
    0.17
    Act Density 0.004%

    No Known Activations