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

    Neuronpedia

    INDEX
    Explanations

    names of researchers and co-authors in academic publications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.79
     himo
    -0.76
     hiszen
    -0.68
    ñadir
    -0.68
    wikidata
    -0.67
    millimeters
    -0.66
    <>());
    -0.66
    مرح
    -0.65
    ]-->
    -0.65
    Personendaten
    -0.64
    POSITIVE LOGITS
     attemp
    1.70
     maneu
    1.69
     impra
    1.63
     depic
    1.59
     encomp
    1.58
     inappro
    1.55
     reluct
    1.52
     strick
    1.51
     increa
    1.50
     inev
    1.49
    Act Density 0.163%

    No Known Activations