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

    Neuronpedia

    INDEX
    Explanations

    references to clothing or what individuals are wearing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pritchard
    -0.75
    (',')
    -0.73
     Biggs
    -0.73
     Humphries
    -0.73
    loß
    -0.68
    время
    -0.67
    ApiProperty
    -0.67
    idopsis
    -0.67
    ízo
    -0.67
     Pollack
    -0.66
    POSITIVE LOGITS
     wear
    2.23
     Wear
    2.16
    Wear
    2.04
     wears
    2.00
     worn
    1.97
     WEAR
    1.92
    wear
    1.89
     wearing
    1.83
     wore
    1.80
     Wearing
    1.78
    Act Density 0.035%

    No Known Activations