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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     in
    0.82
    the
    0.73
     the
    0.69
     في
    0.64
     O
    0.63
     По
    0.63
     (
    0.62
     Y
    0.61
     Z
    0.60
     y
    0.60
    POSITIVE LOGITS
    ێنی
    0.72
    akaranam
    0.61
    attlist
    0.59
    🔡
    0.58
     doxy
    0.55
     υπάρχ
    0.55
    nalia
    0.55
    ціа
    0.54
    내
    0.54
    ಶ್ಚ
    0.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.