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

    Neuronpedia

    INDEX
    Explanations

    percentages related to statistics or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mountaine
    -0.65
    laşı
    -0.64
    </i>
    -0.64
    ται
    -0.63
     Wille
    -0.61
    illo
    -0.56
    csak
    -0.56
    );*/
    -0.56
    el
    -0.54
    loč
    -0.53
    POSITIVE LOGITS
     \%$
    1.03
    Portail
    0.97
    %
    0.94
    %+
    0.85
    .*")]
    0.83
    \%
    0.83
    fromCharCode
    0.80
    %*
    0.80
     \%}$
    0.78
    %"
    0.78
    Act Density 0.193%

    No Known Activations