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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     attempts
    0.84
     taas
    0.76
     thứ
    0.75
     pocas
    0.71
     данной
    0.71
     externas
    0.71
     intentos
    0.71
     اړه
    0.71
     attachments
    0.70
     tropas
    0.70
    POSITIVE LOGITS
    élément
    0.86
    ן
    0.83
    ש
    0.78
     élément
    0.76
     perché
    0.76
    ᠮ
    0.71
    èque
    0.71
    🍶
    0.70
    خ
    0.70
     sensation
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.