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

    Neuronpedia

    INDEX
    Explanations

    Descriptions of building heights and floor counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.73
     للمعارف
    -0.66
     transfieras
    -0.64
     okuyayım
    -0.61
    RenderAtEndOf
    -0.60
    bkz
    -0.59
    VolleyError
    -0.58
    Geplaatst
    -0.57
    WriteTagHelper
    -0.56
     للاسماء
    -0.56
    POSITIVE LOGITS
     floor
    0.81
     floors
    0.77
     level
    0.75
     étage
    0.74
     étages
    0.71
    층
    0.70
     mezzanine
    0.67
     levels
    0.66
     Level
    0.65
     Floor
    0.65
    Act Density 0.013%

    No Known Activations