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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trends or changes in social or cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ility
    -0.15
     Thread
    -0.14
    agn
    -0.14
    ilities
    -0.13
    urtle
    -0.13
    zee
    -0.13
    wan
    -0.13
     kür
    -0.13
    iltr
    -0.13
     consul
    -0.12
    POSITIVE LOGITS
     Ñģобой
    0.19
    ÑĦик
    0.15
    orro
    0.14
     ÑģобоÑİ
    0.14
    æĦı
    0.14
    lamaz
    0.14
    опол
    0.14
    ãĤ¿ãĥ¼
    0.13
     عد
    0.13
    eful
    0.13
    Act Density 0.158%

    No Known Activations