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

    Neuronpedia

    INDEX
    Explanations

    descriptions of clothing attributes and fit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     screwed
    -0.14
    ale
    -0.14
    uploader
    -0.14
     enamel
    -0.14
     ster
    -0.14
     upside
    -0.14
     stead
    -0.14
     thơm
    -0.14
    aled
    -0.14
     Blond
    -0.13
    POSITIVE LOGITS
     cin
    0.23
    midi
    0.23
     flattering
    0.21
    /loose
    0.21
     loose
    0.20
     midi
    0.20
     length
    0.19
    hang
    0.19
     hangs
    0.19
     дли
    0.18
    Act Density 0.065%

    No Known Activations