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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of office locations

    oai_token-act-pair · gpt-3.5-turbo

    references to administrative offices and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nia
    -0.71
    rous
    -0.71
    ebook
    -0.70
    Doctors
    -0.67
    COMPLE
    -0.66
    Enough
    -0.66
    Pause
    -0.65
    thia
    -0.65
    ANC
    -0.65
    Beg
    -0.65
    POSITIVE LOGITS
     offices
    1.06
    holders
    0.90
    office
    0.90
    holder
    0.86
     desks
    0.86
     glim
    0.81
    tops
    0.79
     office
    0.78
     drawer
    0.77
    matically
    0.77
    Act Density 0.012%

    No Known Activations