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

    Neuronpedia

    INDEX
    Explanations

    references to statistical comparisons and factors related to gender pay equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Einfluß
    -0.61
     daß
    -0.60
     peur
    -0.58
     perchè
    -0.56
     muß
    -0.54
     chrétien
    -0.53
    luß
    -0.53
     disparition
    -0.52
     läßt
    -0.51
     trattato
    -0.51
    POSITIVE LOGITS
    =$?
    0.70
    . 
    0.68
     surla
    0.67
    $​
    0.65
    ՚
    0.64
    ́n
    0.63
    .”—
    0.63
    arithmic
    0.62
    }$​
    0.62
     “(
    0.61
    Act Density 0.269%

    No Known Activations