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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🛒
    0.81
    ➎
    0.77
    Subscriber
    0.75
    Respiratory
    0.74
    🚇
    0.72
    Gill
    0.71
    ný
    0.71
    Ϥ
    0.71
    ₡
    0.71
    Detection
    0.70
    POSITIVE LOGITS
     corrupt
    1.02
     corrupted
    0.89
     corruption
    0.88
     dement
    0.88
     benevolent
    0.88
     mortality
    0.85
     bond
    0.85
     cruel
    0.84
     generations
    0.83
     brutality
    0.83
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.