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

    Neuronpedia

    INDEX
    Explanations

    references to clothing and protective gear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wholesome
    -0.46
     domestic
    -0.45
    domestic
    -0.45
    bucht
    -0.44
     Domestic
    -0.44
    urgie
    -0.43
     globos
    -0.42
     minuta
    -0.42
     domestiques
    -0.41
    ooga
    -0.41
    POSITIVE LOGITS
     worn
    1.36
     wearer
    1.28
     wear
    1.09
     Wear
    1.08
    Wearing
    1.07
     Wearing
    1.05
     wearing
    1.04
     donned
    1.04
     Worn
    1.04
    Wear
    0.99
    Act Density 0.208%

    No Known Activations