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

    Neuronpedia

    INDEX
    Explanations

    special markers or sections within structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.50
    stag
    -0.48
    アウト
    -0.47
    訳
    -0.46
     насељу
    -0.46
     R
    -0.45
     her
    -0.43
     f
    -0.43
    ti
    -0.42
     I
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.83
     חיצוניים
    0.82
    IVEREF
    0.82
    PyExc
    0.81
    ValueStyle
    0.81
    EDEFAULT
    0.79
    InjectAttribute
    0.79
    NewUrlParser
    0.75
     Roskov
    0.74
    atguigu
    0.74
    Act Density 0.010%

    No Known Activations