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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.36
    <?
    -0.79
     intersper
    -0.68
     inaugurate
    -0.66
    /***
    -0.65
     assiste
    -0.63
    <!--
    -0.62
    ⓧ
    -0.61
    Дереккөздер
    -0.61
     endow
    -0.61
    POSITIVE LOGITS
     Minang
    0.80
     ananas
    0.79
     bandung
    0.76
     télévis
    0.75
     chré
    0.74
     camry
    0.74
     useRouter
    0.72
     brune
    0.71
     jawa
    0.70
     COMPOUNDS
    0.67
    Act Density 0.347%

    No Known Activations