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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ERATE
    1.39
    𝘦
    1.39
    𝘭
    1.26
    𝘱
    1.25
    DeviceCompliance
    1.22
    ȟ
    1.20
    TY
    1.19
    '`--
    1.19
    houette
    1.18
    <unused937>
    1.15
    POSITIVE LOGITS
    뉴
    1.06
    獄
    0.94
    ש
    0.93
    Former
    0.93
     spel
    0.92
    ケース
    0.92
     پا
    0.92
    State
    0.91
    בד
    0.90
     sto
    0.90
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.