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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and feedback in a formal or positive manner

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.30
    <?
    -0.82
    
    -0.81
    /***
    -0.75
    ⓧ
    -0.75
    /**
    -0.74
    <?
    -0.73
    deinit
    -0.71
    /*!
    -0.70
    bzero
    -0.65
    POSITIVE LOGITS
     Minang
    1.61
     bandung
    1.47
     thut
    1.44
     mef
    1.44
     stockholm
    1.39
     maneu
    1.38
     Juf
    1.37
     Jambi
    1.36
     increa
    1.35
     Banjar
    1.35
    Act Density 0.141%

    No Known Activations