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

    Neuronpedia

    INDEX
    Explanations

    measurements related to weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.04
    ⓧ
    -0.92
    
    -0.89
    /**
    -0.88
    <?
    -0.75
    webElementXpaths
    -0.73
    /*
    -0.72
     betweenstory
    -0.70
    Билгалдахарш
    -0.64
     ProtoMessage
    -0.64
    POSITIVE LOGITS
     jaya
    0.88
     maroc
    0.86
     giovanni
    0.82
     Minang
    0.81
     jawa
    0.79
     bandung
    0.75
     napoli
    0.75
     hansen
    0.74
     jati
    0.74
     gatti
    0.72
    Act Density 0.056%

    No Known Activations