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

    Neuronpedia

    INDEX
    Explanations

    statements about accuracy, correctness, and compliance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.40
    /***
    -0.87
    
    -0.87
    displayquote
    -0.81
    /*
    -0.76
    /**
    -0.76
    <tfoot>
    -0.73
    /*!
    -0.73
    Kontrola
    -0.72
    //---
    -0.72
    POSITIVE LOGITS
     maroc
    1.45
     lidl
    1.42
     riviera
    1.41
     stockholm
    1.33
     milano
    1.29
     paradiso
    1.29
     bordeaux
    1.29
     outlander
    1.29
     matel
    1.26
     Meksi
    1.26
    Act Density 1.774%

    No Known Activations