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

    Neuronpedia

    INDEX
    Explanations

    propper names related to "Rapunzel"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Rapunzel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.77
     Afgh
    -0.71
     Lebanese
    -0.70
     Samar
    -0.65
    lda
    -0.63
    perse
    -0.63
     Borders
    -0.62
    bred
    -0.62
     Lumpur
    -0.61
    WHERE
    -0.61
    POSITIVE LOGITS
    acious
    1.26
    itone
    1.04
    acity
    1.03
    ework
    0.92
    aic
    0.89
    hett
    0.89
    ename
    0.89
    ids
    0.89
    acus
    0.88
    aciously
    0.87
    Act Density 0.024%

    No Known Activations