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

    Neuronpedia

    INDEX
    Explanations

    references to speakers in political or formal settings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.88
    ⓧ
    -1.06
    
    -0.95
    <?
    -0.89
    /*
    -0.81
    /**
    -0.79
    /***
    -0.68
    Vegeu
    -0.66
    Enllaços
    -0.59
    #![
    -0.59
    POSITIVE LOGITS
     bandung
    1.27
     dises
    1.27
     speaker
    1.24
     Speakers
    1.22
     Czechos
    1.18
     Minang
    1.17
     SPEAKER
    1.17
     Meksi
    1.16
     alpes
    1.15
     Speaker
    1.15
    Act Density 0.103%

    No Known Activations