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

    Neuronpedia

    INDEX
    Explanations

    references to "office" and related terminology in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.77
    isContained
    -0.76
    Đây
    -0.71
     vt
    -0.68
    TagMode
    -0.67
     vad
    -0.67
     Catan
    -0.67
     Verbraucher
    -0.67
    redients
    -0.66
    angering
    -0.65
    POSITIVE LOGITS
     office
    1.70
     offices
    1.70
     Office
    1.60
    office
    1.53
     Offices
    1.51
     OFFICE
    1.49
    Office
    1.47
    offices
    1.40
    OFFICE
    1.36
     OFFICES
    1.28
    Act Density 0.034%

    No Known Activations