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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Les."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.59
    /**
    -0.79
    <?
    -0.77
     Quoi
    -0.74
     Aún
    -0.72
    
    -0.69
     Aucune
    -0.69
     Autre
    -0.68
    jątk
    -0.67
     Celui
    -0.67
    POSITIVE LOGITS
     Les
    1.29
     LES
    1.15
    Les
    1.13
     les
    1.06
     hina
    1.03
     saar
    1.02
    les
    0.96
     Las
    0.95
     magis
    0.94
     sii
    0.91
    Act Density 0.080%

    No Known Activations