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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dissimilar
    1.04
    с
    1.02
    ㄱ
    0.98
     typical
    0.95
     truly
    0.95
     eccentric
    0.92
     inferior
    0.91
     refractory
    0.88
     indigenous
    0.86
     stately
    0.86
    POSITIVE LOGITS
    ahiran
    1.55
    urals
    1.33
    ialize
    1.32
    azienda
    1.30
    ၞ
    1.29
    1.29
    ronics
    1.28
     részt
    1.28
    orgt
    1.27
     интел
    1.27
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.