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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Developers
    -0.75
    ĸļ
    -0.72
    Introduced
    -0.69
    zx
    -0.66
    sein
    -0.65
     Tian
    -0.62
    èĢħ
    -0.62
    Developer
    -0.61
    arthed
    -0.60
    İĭ
    -0.60
    POSITIVE LOGITS
    apo
    0.87
    ftime
    0.69
     psy
    0.68
     Inquisition
    0.67
    opian
    0.66
    holiday
    0.64
    SG
    0.63
    istical
    0.61
    RH
    0.61
     Gamble
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.