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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hör
    1.35
    fifths
    1.15
     哦
    1.14
    .</
    1.14
     tangy
    1.10
    revise
    1.08
     الوز
    1.08
    rale
    1.06
     '.</
    1.06
     ब्रा
    1.05
    POSITIVE LOGITS
    GPT
    1.02
    เจ
    0.96
     попы
    0.85
    จับ
    0.85
     +
    0.84
     banyaknya
    0.84
    เต
    0.84
    場所に
    0.83
     sepat
    0.81
    จำนวน
    0.81
    Act Density 0.044%

    No Known Activations