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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.68
     the
    0.46
     a
    0.42
     many
    0.39
     these
    0.38
     I
    0.38
     more
    0.38
     U
    0.37
     an
    0.36
     B
    0.35
    POSITIVE LOGITS
    <unused2091>
    0.79
    <unused1563>
    0.78
    <unused823>
    0.77
    <unused368>
    0.76
    <unused2151>
    0.76
    ଃ
    0.76
    <unused722>
    0.76
    <unused569>
    0.74
    <unused2178>
    0.74
    <unused710>
    0.74
    Act Density 7.185%

    No Known Activations