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

    Neuronpedia

    INDEX
    Explanations

    references to monetary amounts or rates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     madonna
    -0.75
     thut
    -0.69
     increa
    -0.69
     meis
    -0.68
     guarante
    -0.67
     „,
    -0.66
     waer
    -0.66
     tanga
    -0.63
     juf
    -0.62
     kano
    -0.62
    POSITIVE LOGITS
     annum
    0.72
     month
    0.65
     per
    0.59
    /**
    0.59
     week
    0.56
    <?
    0.56
    Chaque
    0.56
     year
    0.55
     day
    0.53
     Capítulo
    0.53
    Act Density 0.097%

    No Known Activations