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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     favoured
    0.48
     celebrated
    0.48
     Вен
    0.48
    ה
    0.48
     uman
    0.47
     Iranian
    0.46
    イ
    0.46
    ه
    0.46
     geography
    0.45
    공
    0.45
    POSITIVE LOGITS
    Paused
    0.43
    capt
    0.43
    鋃
    0.42
    rales
    0.41
    attaa
    0.41
    😱
    0.41
    एं
    0.39
    导致
    0.38
    Bonus
    0.38
    rored
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.