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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.59
     are
    0.53
    竖
    0.48
    <0xE3>
    0.48
     if
    0.47
     a
    0.46
     sua
    0.46
     and
    0.46
     seu
    0.46
     Whole
    0.46
    POSITIVE LOGITS
     overtaking
    0.61
    J
    0.58
    zeptember
    0.53
    ning
    0.50
    vak
    0.50
    OCK
    0.49
    ONDER
    0.49
     wasting
    0.49
    ({\
    0.48
    ningarna
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.