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

    Neuronpedia

    INDEX
    Explanations

    references to bathrooms and associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.96
     autorytatywna
    -0.90
    :✨
    -0.79
    ówczas
    -0.78
    ientôt
    -0.76
     <>",
    -0.75
    ofield
    -0.74
    verständ
    -0.74
    Controllo
    -0.73
     Schofield
    -0.72
    POSITIVE LOGITS
     bathroom
    1.61
     Bathroom
    1.46
     bathrooms
    1.41
    Bathroom
    1.35
     Bathrooms
    1.31
    bathroom
    1.29
    Bathrooms
    1.21
     Badezimmer
    1.00
     łaz
    0.94
     restroom
    0.91
    Act Density 0.046%

    No Known Activations