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

    Neuronpedia

    INDEX
    Explanations

    mentions of full-time employment

    oai_token-act-pair · gpt-3.5-turbo

    references to full-time employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.84
     tomat
    -0.74
    rosis
    -0.74
    ramid
    -0.71
    ̶
    -0.70
    ovember
    -0.69
    hra
    -0.69
    uador
    -0.69
     shatter
    -0.69
    arty
    -0.67
    POSITIVE LOGITS
     employment
    0.93
     equivalents
    0.90
     basis
    0.78
     unemployed
    0.74
     missionary
    0.72
     occupation
    0.72
     Bucc
    0.71
     worker
    0.70
     missionaries
    0.68
     MBA
    0.67
    Act Density 0.032%

    No Known Activations