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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    �
    -0.08
     dann
    -0.07
    ）、
    -0.07
     secondo
    -0.07
     Hun
    -0.07
    焌
    -0.06
    ㈼
    -0.06
     turning
    -0.06
    .Width
    -0.06
    *k
    -0.06
    POSITIVE LOGITS
    櫆
    0.07
    :^
    0.07
    �
    0.07
    משכ
    0.07
    ksen
    0.07
     chambers
    0.07
    _TRANSFER
    0.07
    擢
    0.07
     archival
    0.07
    ────
    0.06
    Act Density 0.010%

    No Known Activations