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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.69
     separation
    -0.67
    atican
    -0.65
     switch
    -0.65
    ESA
    -0.65
    unch
    -0.64
    esa
    -0.62
    olo
    -0.61
    ICT
    -0.60
    ifa
    -0.60
    POSITIVE LOGITS
    ĸļ
    0.90
    ruciating
    0.78
     Archdemon
    0.73
     pestic
    0.70
     Eternity
    0.68
    ared
    0.67
    ¥ŀ
    0.66
     heaven
    0.66
     hindsight
    0.66
    igans
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.