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

    Neuronpedia

    INDEX
    Explanations

    references to a specific entity or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Obrador
    -0.85
    Étymologie
    -0.83
    Personendaten
    -0.79
    帖最后由
    -0.79
    </tfoot>
    -0.77
    turnstile
    -0.75
    -------------</
    -0.75
    belline
    -0.73
    irited
    -0.73
    MLLoader
    -0.73
    POSITIVE LOGITS
    <bos>
    0.59
     autorytatywna
    0.55
    </h2>
    0.48
    $\
    0.43
     surla
    0.41
     
    0.41
    有一定的
    0.39
    the
    0.39
    oredCriteria
    0.38
    M
    0.38
    Act Density 3.848%

    No Known Activations