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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     judged
    0.61
     all
    0.59
     mily
    0.59
     eng
    0.58
     viewed
    0.58
     elaborated
    0.58
     men
    0.57
     ese
    0.57
     gratefully
    0.57
     adjudged
    0.57
    POSITIVE LOGITS
    ﮩ
    0.76
     업무
    0.70
    ཿ
    0.68
    }}$;
    0.67
    ﮗ
    0.67
    ವಿ
    0.65
    azada
    0.64
    ╽
    0.64
     কাজের
    0.63
    alama
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.