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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of outfits

    oai_token-act-pair · gpt-3.5-turbo

    references to clothing and outfits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elaide
    -0.71
    IDER
    -0.67
     breath
    -0.64
     moons
    -0.64
     Examiner
    -0.61
    Cond
    -0.61
    LEASE
    -0.61
    asper
    -0.59
     tablets
    -0.58
     Lith
    -0.58
    POSITIVE LOGITS
    ting
    1.25
    ters
    1.22
    uated
    1.13
    uates
    1.05
    terson
    1.01
    ricia
    0.99
    tering
    0.97
    tered
    0.95
    ted
    0.93
    uate
    0.90
    Act Density 0.058%

    No Known Activations