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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     belang
    -0.08
     colossal
    -0.07
    erti
    -0.07
    È
    -0.07
    มะ
    -0.07
     figura
    -0.07
     formidable
    -0.07
    :numel
    -0.07
    𝓁
    -0.07
    hoc
    -0.07
    POSITIVE LOGITS
    活动
    0.07
    errors
    0.07
    _connection
    0.07
    换
    0.06
     LM
    0.06
    变化
    0.06
    .Margin
    0.06
     accuracy
    0.06
    忧
    0.06
    事宜
    0.06
    Act Density 0.004%

    No Known Activations