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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated formatting or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.15
    }*/
    -1.03
    */;
    -0.93
    "),
    -0.89
    )");
    -0.87
    )";
    -0.87
    };*/
    -0.86
    '},
    -0.86
    ſelf
    -0.86
    '),
    -0.85
    POSITIVE LOGITS
    0
    1.51
     hundred
    0.84
    1
    0.81
    hundred
    0.80
    ۰۰
    0.77
    thousand
    0.73
     Hundred
    0.70
     thousand
    0.69
    3
    0.67
     million
    0.66
    Act Density 0.549%

    No Known Activations