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

    Neuronpedia

    INDEX
    Explanations

    placeholder symbols used in formatted output

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukone
    -0.71
    省市镇
    -0.68
     Einer
    -0.66
    ]";
    -0.66
    -0.65
     Endless
    -0.63
    Endless
    -0.62
     ın
    -0.62
    لیس
    -0.62
    )');
    -0.61
    POSITIVE LOGITS
    ("%
    1.01
    ('%
    0.92
    ,"%
    0.91
    ="%
    0.79
    :%
    0.76
     "%
    0.76
    ='%
    0.76
     '%
    0.72
    coration
    0.72
    
    0.71
    Act Density 0.038%

    No Known Activations