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

    Neuronpedia

    INDEX
    Explanations

    terms related to machine learning processes and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tong
    -0.16
    obot
    -0.14
    969
    -0.14
    liers
    -0.14
     Mort
    -0.14
     impl
    -0.14
    鸡
    -0.14
     numbered
    -0.14
    /lg
    -0.14
    <<<
    -0.13
    POSITIVE LOGITS
     saver
    0.26
     sess
    0.25
     tf
    0.25
    =tf
    0.23
    tf
    0.21
    (tf
    0.21
    TF
    0.19
    sess
    0.19
     TF
    0.18
     placeholders
    0.17
    Act Density 0.002%

    No Known Activations