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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     seating
    0.71
            
    0.68
     Cholesterol
    0.66
    sev
    0.64
     사항
    0.64
    사항
    0.63
    ствие
    0.61
    rotation
    0.61
    деб
    0.61
    ي
    0.61
    POSITIVE LOGITS
    ייתה
    0.82
    یں
    0.79
    あるいは
    0.77
     undeniable
    0.77
    ians
    0.73
    或者是
    0.73
    或者
    0.71
     kasnije
    0.71
     mengungkap
    0.70
     collaborators
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.