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

    Neuronpedia

    INDEX
    Explanations

    descriptive language related to products and services

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.34
    /***
    -0.90
    ⓧ
    -0.78
    Vegeu
    -0.65
    /**
    -0.65
    <?
    -0.64
    
    -0.62
    MockBean
    -0.58
    /*
    -0.56
    Тру
    -0.55
    POSITIVE LOGITS
     jaya
    1.00
     daz
    0.94
     benzina
    0.93
     bloss
    0.91
     bayern
    0.90
     saad
    0.90
     meis
    0.90
     frankfurt
    0.90
     kyo
    0.90
     hina
    0.89
    Act Density 0.643%

    No Known Activations