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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to professionals in various fields

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.15
    /**
    -1.00
    
    -0.96
    ⓧ
    -0.94
    <?
    -0.88
    <?
    -0.74
    /***
    -0.71
    /*
    -0.68
     ceded
    -0.67
    /*!
    -0.66
    POSITIVE LOGITS
     professionals
    1.30
    professionals
    1.21
     Professionals
    1.14
     saar
    1.14
     jaya
    1.11
     experts
    1.01
     seksi
    0.99
     Minang
    0.98
     kafe
    0.98
     lele
    0.97
    Act Density 0.172%

    No Known Activations