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

    Neuronpedia

    INDEX
    Explanations

    Biblical references and religious terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.70
    ⓧ
    -1.50
    /**
    -1.29
    
    -1.27
    <?
    -1.07
    /*
    -1.01
    <?
    -0.99
    /***
    -0.76
    JAKARTA
    -0.74
    /*++
    -0.71
    POSITIVE LOGITS
     maneu
    1.05
     increa
    1.01
     Minang
    0.96
     vry
    0.94
     daz
    0.92
     impra
    0.91
     lele
    0.91
     coö
    0.90
     Præ
    0.90
     affor
    0.87
    Act Density 0.093%

    No Known Activations