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

    Neuronpedia

    INDEX
    Explanations

    mention of undergarments, specifically underwear and panties

    oai_token-act-pair · gpt-3.5-turbo

    references to undergarments and related clothing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.78
    iard
    -0.74
    actic
    -0.73
    resp
    -0.70
    eto
    -0.69
    opal
    -0.66
     Crow
    -0.66
    obal
    -0.65
    OVER
    -0.65
    cour
    -0.64
    POSITIVE LOGITS
     underwear
    1.13
     drawer
    0.85
    skirts
    0.84
     panties
    0.75
    essional
    0.73
     sleeves
    0.73
     bras
    0.73
     worn
    0.73
     EDITION
    0.71
    wrap
    0.71
    Act Density 0.023%

    No Known Activations