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

    Neuronpedia

    INDEX
    Explanations

    words related to salaries and positions in a business context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Engels
    -0.81
    ledged
    -0.73
     Jenner
    -0.69
    atform
    -0.62
     guiIcon
    -0.62
     skelet
    -0.61
     Pigs
    -0.61
     brackets
    -0.55
    lez
    -0.55
    mma
    -0.54
    POSITIVE LOGITS
    inki
    0.81
    egu
    0.77
    uddin
    0.75
    eeds
    0.74
    opol
    0.73
    ieri
    0.72
    ety
    0.69
    oad
    0.68
    eed
    0.68
    aimon
    0.67
    Act Density 0.400%

    No Known Activations