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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.89
     மற்ற
    -0.69
     xxiii
    -0.66
     xxii
    -0.66
     xxiv
    -0.63
     xxvi
    -0.60
     소녀
    -0.58
     xxi
    -0.58
     xxv
    -0.57
    đồ
    -0.54
    POSITIVE LOGITS
     bamb
    1.04
     fré
    1.02
    dirond
    1.00
     quoique
    1.00
     cyr
    0.99
     nutr
    0.98
     parati
    0.94
    quarelle
    0.94
     exé
    0.94
     apparti
    0.93
    Act Density 0.167%

    No Known Activations