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

    Neuronpedia

    INDEX
    Explanations

    highly engaged phrases related to viewer ratings or success metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PyObject
    -0.43
     motorcycles
    -0.39
     unmarried
    -0.37
    邏
    -0.36
     MutableLiveData
    -0.36
    atural
    -0.35
    дах
    -0.35
    逻辑
    -0.35
    separation
    -0.35
     BaseModel
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.69
    setVerticalGroup
    0.59
     للمعارف
    0.59
     disambiguazione
    0.58
     ***!
    0.57
     kasarigan
    0.55
     &___
    0.54
     مشين
    0.52
    点此举报
    0.51
     nahilalakip
    0.50
    Act Density 0.093%

    No Known Activations