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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    시켜
    0.85
    시키는
    0.84
    시킨
    0.80
     الجديد
    0.72
    시키
    0.69
     Между
    0.69
    ზ
    0.67
    हत्या
    0.65
    ষ্ণ
    0.65
    classroom
    0.64
    POSITIVE LOGITS
    ️⃣
    1.12
    ⃣
    0.97
    d
    0.81
    iligung
    0.70
    re
    0.70
    enang
    0.67
    daa
    0.65
    dagen
    0.65
    ังสือ
    0.63
    ITIES
    0.62
    Act Density 0.132%

    No Known Activations