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

    Neuronpedia

    INDEX
    Explanations

    references to full-time jobs or employment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
    LCS
    -0.78
    ovember
    -0.77
    ambo
    -0.75
    ombs
    -0.71
    Reward
    -0.71
    hra
    -0.71
    uador
    -0.71
    arest
    -0.71
    asty
    -0.70
    POSITIVE LOGITS
     equivalents
    1.02
     employment
    1.00
     basis
    0.90
     worker
    0.84
     missionary
    0.80
     employee
    0.79
     unemployed
    0.77
     equivalent
    0.76
     wage
    0.76
     jobs
    0.74
    Act Density 0.054%

    No Known Activations