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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    romatic
    0.45
    ítése
    0.38
    re
    0.38
     pleasant
    0.38
    во
    0.37
    razione
    0.37
     powodu
    0.37
    ți
    0.35
    ch
    0.35
    était
    0.34
    POSITIVE LOGITS
     oleh
    0.87
     by
    0.85
    ໂດຍ
    0.68
     توسط
    0.63
     بواسطة
    0.63
    โดย
    0.60
     By
    0.55
     από
    0.54
     ACLU
    0.54
     Fundação
    0.52
    Act Density 0.017%

    No Known Activations