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

    Neuronpedia

    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.99
    ⓧ
    -1.01
    /***
    -0.79
    
    -0.77
    /**
    -0.77
    public
    -0.76
    })();
    -0.76
    <?
    -0.75
    override
    -0.74
    /*
    -0.73
    POSITIVE LOGITS
     maneu
    2.14
     affor
    2.10
     aen
    2.06
     emphat
    2.00
     impra
    2.00
     accla
    1.94
     increa
    1.93
     fta
    1.93
     wien
    1.91
     fluo
    1.89
    Act Density 0.058%

    No Known Activations