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

    Neuronpedia

    INDEX
    Explanations

    mentions of 'Saint' as part of a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    references to "Saint" followed by a place or title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIP
    -0.88
    PT
    -0.75
    ERG
    -0.73
    ORN
    -0.73
    razil
    -0.73
    PN
    -0.71
    OTH
    -0.69
    JUST
    -0.67
    iferation
    -0.66
    HO
    -0.66
    POSITIVE LOGITS
     Laurent
    0.99
    onew
    0.89
    arts
    0.84
     Louis
    0.83
     Clair
    0.81
     Lucia
    0.78
    ifully
    0.78
    clair
    0.77
     Augustine
    0.76
     Petersburg
    0.75
    Act Density 0.012%

    No Known Activations