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

    Neuronpedia

    INDEX
    Explanations

    mentions of movies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.31
    ⓧ
    -0.96
    /**
    -0.94
    /*
    -0.88
    <?
    -0.84
    
    -0.81
    /***
    -0.80
    <?
    -0.71
    #![
    -0.70
    /*++
    -0.67
    POSITIVE LOGITS
     Juf
    1.36
     Keny
    1.36
     Intere
    1.31
     véhic
    1.25
     Khart
    1.23
     Manufact
    1.23
     Minang
    1.22
     Hano
    1.22
     saar
    1.21
     Augu
    1.20
    Act Density 0.078%

    No Known Activations