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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    BOOK
    -0.77
    helps
    -0.74
    HM
    -0.73
    olas
    -0.73
    itiz
    -0.73
    CHQ
    -0.72
    eters
    -0.72
    OLD
    -0.72
    anamo
    -0.70
    ouk
    -0.69
    POSITIVE LOGITS
     Resurrection
    0.76
     Redemption
    0.74
     Saturn
    0.66
     Survivor
    0.64
     Roller
    0.64
     endings
    0.63
     elimination
    0.63
     expulsion
    0.62
     Scythe
    0.62
     Sabbath
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.