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

    Neuronpedia

    INDEX
    Explanations

    references to political events and community initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.05
     /**
    -0.64
     their
    -0.64
    <?
    -0.62
    ///**
    -0.62
     these
    -0.62
    /***
    -0.61
    public
    -0.61
     his
    -0.60
    this
    -0.60
    POSITIVE LOGITS
     accla
    1.49
     affor
    1.48
     lidl
    1.42
     maneu
    1.36
     impra
    1.33
     excru
    1.30
     stockholm
    1.30
     increa
    1.29
     sovere
    1.28
     unden
    1.27
    Act Density 2.450%

    No Known Activations