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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professional or academic development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectF
    -0.44
    ACKNOWLEDGMENT
    -0.43
    str
    -0.43
    hasData
    -0.43
     المعيارى
    -0.42
    Màu
    -0.42
     ingenu
    -0.42
    setConfig
    -0.41
    Puss
    -0.41
    olia
    -0.40
    POSITIVE LOGITS
     BECOME
    0.96
    become
    0.92
     Become
    0.88
    became
    0.87
     become
    0.85
    Become
    0.83
    becomes
    0.82
     Becomes
    0.82
     Became
    0.80
     becoming
    0.77
    Act Density 0.135%

    No Known Activations