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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    od
    0.95
    pt
    0.82
    a
    0.81
    ul
    0.80
    per
    0.80
    h
    0.79
    ed
    0.77
    ar
    0.76
    led
    0.76
    며
    0.76
    POSITIVE LOGITS
     sacraments
    0.91
     dhammo
    0.86
     attacks
    0.86
     capsid
    0.86
    ຈະ
    0.85
    ेच्छा
    0.85
     Elapsed
    0.85
     addicts
    0.83
    隘
    0.82
    Ĩ
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.