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

    Neuronpedia

    INDEX
    Explanations

    proper names and specific terms mentioned in the text passages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.61
    
    -0.71
    <?
    -0.68
    //
    -0.65
    /***
    -0.65
                    
    -0.65
    ുറ
    -0.64
    -0.64
    public
    -0.63
                
    -0.63
    POSITIVE LOGITS
     maneu
    1.86
     stockholm
    1.80
     affor
    1.79
     Known
    1.69
     increa
    1.67
     accla
    1.63
     milf
    1.63
     sappi
    1.59
     peppa
    1.58
     known
    1.58
    Act Density 0.084%

    No Known Activations