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

    Neuronpedia

    INDEX
    Explanations

    references to clothing or attire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pritchard
    -0.71
     Biggs
    -0.65
     Alves
    -0.63
    ContentAsync
    -0.63
    stüt
    -0.62
    IsContent
    -0.60
     Pollack
    -0.60
     abzu
    -0.60
    来不及
    -0.60
     يتيمه
    -0.59
    POSITIVE LOGITS
     wear
    3.22
     Wear
    3.03
    Wear
    2.82
     wears
    2.74
     WEAR
    2.74
    wear
    2.69
     wore
    2.55
     wearing
    2.54
     worn
    2.50
     Wearing
    2.38
    Act Density 0.053%

    No Known Activations