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

    Neuronpedia

    INDEX
    Explanations

    references to office-related concepts and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.90
     vad
    -0.76
     Catan
    -0.74
     vt
    -0.70
    nt
    -0.69
    Đây
    -0.68
    ly
    -0.67
    angering
    -0.66
     Caus
    -0.65
     Verbraucher
    -0.65
    POSITIVE LOGITS
     offices
    1.58
     office
    1.52
     Office
    1.43
     Offices
    1.41
    office
    1.36
     OFFICE
    1.35
    offices
    1.30
    Office
    1.29
    OFFICE
    1.23
     OFFICES
    1.20
    Act Density 0.033%

    No Known Activations