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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ه
    1.35
    س
    1.34
    ל
    1.34
    ä
    1.27
    <0xA1>
    1.16
    ה
    1.16
    v
    1.10
    ING
    1.09
    ب
    1.08
    a
    1.07
    POSITIVE LOGITS
     as
    1.09
    '
    1.03
    ika
    1.00
    ights
    0.95
    ibr
    0.94
     apariencia
    0.93
    ั
    0.93
    로는
    0.91
     malicious
    0.90
    ↵↵
    0.89
    Act Density 0.000%

    No Known Activations