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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     NO
    1.78
     !!
    1.70
     !!!
    1.60
     :
    1.52
     !!!!
    1.48
      
    1.47
     :-
    1.37
     !!!!!
    1.35
    1.35
     ::
    1.35
    POSITIVE LOGITS
    ແລະ
    1.94
    ették
    1.89
     পাওয়
    1.80
    ल्यावर
    1.77
    ând
    1.73
    nię
    1.73
    annya
    1.66
    पहरण
    1.65
    ंती
    1.64
    และ
    1.64
    Act Density 0.000%

    No Known Activations