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

    Neuronpedia

    INDEX
    Explanations

    repeated elements or patterns characteristic of code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.88
    GeoNames
    -0.81
    хьтан
    -0.77
    楔
    -0.77
    Digitized
    -0.76
    IntoConstraints
    -0.76
    SpringRunner
    -0.74
     Realt
    -0.73
     JAXBElement
    -0.72
     odkazy
    -0.72
    POSITIVE LOGITS
    //
    1.27
    ///
    1.11
    [toxicity=0]
    0.99
    //
    0.91
     *
    0.79
    *
    0.77
    /******/
    0.77
    //*
    0.77
     ↑
    0.74
    ​
    0.69
    Act Density 0.053%

    No Known Activations