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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Programming
    -0.09
     þ
    -0.08
    .table
    -0.07
     transforming
    -0.07
    oming
    -0.06
    tos
    -0.06
     Timestamp
    -0.06
     âm
    -0.06
    乾
    -0.06
    Spot
    -0.06
    POSITIVE LOGITS
    ョン
    0.07
    odeled
    0.07
    꼴
    0.07
    �
    0.06
    detalle
    0.06
    关门
    0.06
    crawl
    0.06
     הדבר
    0.06
    _coeffs
    0.06
    濡
    0.06
    Act Density 0.001%

    No Known Activations