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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     iletişim
    -0.07
     Okay
    -0.07
     söyledi
    -0.07
     وهذا
    -0.07
     afs
    -0.07
     Yes
    -0.07
    email
    -0.07
    '));↵↵
    -0.07
    說話
    -0.06
    :get
    -0.06
    POSITIVE LOGITS
    ители
    0.07
    サー
    0.07
     ל
    0.07
    嫌疑人
    0.07
    тики
    0.07
    /disc
    0.07
    호
    0.07
    立ち
    0.07
    蹈
    0.06
    	th
    0.06
    Act Density 0.001%

    No Known Activations