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

    Neuronpedia

    INDEX
    Explanations

    references to offices or office-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.91
     Catan
    -0.76
     Kunt
    -0.75
    theless
    -0.74
    Đây
    -0.72
    isContained
    -0.69
     ganas
    -0.69
     vt
    -0.69
    LEncoder
    -0.69
     pitié
    -0.68
    POSITIVE LOGITS
     offices
    1.56
     office
    1.54
     Office
    1.41
     OFFICE
    1.35
    office
    1.34
     Offices
    1.32
    Office
    1.28
    offices
    1.24
    OFFICE
    1.18
     OFFICES
    1.12
    Act Density 0.062%

    No Known Activations