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

    Neuronpedia

    INDEX
    Explanations

    terms related to keyboard layout and case sensitivity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "");
    -0.65
    ýš
    -0.61
     />);
    -0.56
     sondern
    -0.53
    $)$
    -0.52
    architecte
    -0.52
     "));
    -0.51
     */
    -0.51
    neum
    -0.50
    期刊论文
    -0.50
    POSITIVE LOGITS
    ThroughAttribute
    0.83
    NameInMap
    0.70
    Regressor
    0.67
    saraba
    0.65
     Taktlose
    0.60
     <=",
    0.59
    таратура
    0.59
     linkovi
    0.57
    AutoScale
    0.56
     >=",
    0.56
    Act Density 0.277%

    No Known Activations