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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kered
    -0.80
    geoning
    -0.77
    autical
    -0.75
    ongyang
    -0.75
    oids
    -0.72
    ilty
    -0.72
    ologies
    -0.70
    onut
    -0.70
    orpor
    -0.70
    enium
    -0.70
    POSITIVE LOGITS
     Archdemon
    0.70
     totality
    0.66
    nesota
    0.63
     constant
    0.60
     provisional
    0.59
     Port
    0.59
     adapter
    0.59
     winters
    0.58
     transformer
    0.58
    Quote
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.