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

    Neuronpedia

    INDEX
    Explanations

    references to offices and workplace environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.92
     Catan
    -0.72
     vad
    -0.71
    ly
    -0.70
     vt
    -0.68
    Đây
    -0.67
    isContained
    -0.66
    nt
    -0.65
    jang
    -0.65
     Caus
    -0.65
    POSITIVE LOGITS
     offices
    1.64
     office
    1.59
     Office
    1.49
     Offices
    1.44
    office
    1.42
     OFFICE
    1.41
    offices
    1.35
    Office
    1.35
    OFFICE
    1.28
     OFFICES
    1.23
    Act Density 0.031%

    No Known Activations