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

    Neuronpedia

    INDEX
    Explanations

    numerical values or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <eos>
    -0.51
     tru
    -0.49
     try
    -0.46
     Long
    -0.45
    GGT
    -0.44
     
    -0.44
    ôn
    -0.44
     X
    -0.43
     attention
    -0.43
     Mart
    -0.43
    POSITIVE LOGITS
    0.97
    Hentet
    0.96
     ThemeData
    0.88
    findpost
    0.84
     سكانية
    0.83
     Pliny
    0.81
    ViewFeatures
    0.80
     sternum
    0.79
    autorest
    0.77
     ویکی‌پدیا
    0.77
    Act Density 0.013%

    No Known Activations