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

    Neuronpedia

    INDEX
    Explanations

    information related to event details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -1.30
    /**
    -1.04
    
    -1.00
    <?
    -0.97
    /*
    -0.84
    <?
    -0.73
    /***
    -0.70
    /*!
    -0.69
    Transcripción
    -0.67
    POSITIVE LOGITS
     seksi
    1.26
     kafe
    1.09
     keramik
    1.04
     maksi
    0.99
     mikrofon
    0.95
     silikon
    0.95
    fordable
    0.94
     alkoh
    0.91
     magis
    0.91
     practition
    0.90
    Act Density 0.285%

    No Known Activations