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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     circa
    0.68
     nelle
    0.66
     or
    0.63
     nell
    0.63
     after
    0.62
     so
    0.61
     nel
    0.61
     tempo
    0.61
     conno
    0.61
     comparable
    0.60
    POSITIVE LOGITS
    ش
    0.93
    ور
    0.73
    نا
    0.72
    Puedes
    0.72
    وا
    0.67
    Puede
    0.67
    ن
    0.66
    ض
    0.64
    ها
    0.64
     أم
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.