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

    Neuronpedia

    INDEX
    Explanations

    mentions of job titles or positions within a company

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maneu
    -1.74
     increa
    -1.58
     inev
    -1.57
     effe
    -1.56
     depic
    -1.55
     thut
    -1.54
     fortn
    -1.52
     encomp
    -1.52
     »>
    -1.50
     guarante
    -1.49
    POSITIVE LOGITS
     own
    0.79
    s
    0.71
     كومونز
    0.68
     للاسماء
    0.67
    存于互联网档案馆
    0.65
     biggest
    0.64
    own
    0.61
     largest
    0.58
     official
    0.57
     ability
    0.57
    Act Density 0.171%

    No Known Activations