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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     сім
    0.95
     auditions
    0.90
     oligarch
    0.88
     chagrin
    0.84
     estranged
    0.83
     frustrations
    0.82
     passo
    0.80
     furo
    0.80
     omitted
    0.79
     sacerdote
    0.78
    POSITIVE LOGITS
    TAIN
    0.86
    ্
    0.75
    ht
    0.75
    Ö
    0.75
    ust
    0.73
    ung
    0.73
    ü
    0.73
    本质
    0.71
    ched
    0.71
    τέ
    0.71
    Act Density 0.000%

    No Known Activations