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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    occupied
    1.28
    timer
    1.27
    easily
    1.25
    greedy
    1.23
    습니다
    1.23
    dangerous
    1.22
    dream
    1.20
    young
    1.19
    dated
    1.19
    었습니다
    1.17
    POSITIVE LOGITS
     η
    1.09
     negozi
    1.09
    λί
    1.04
     "|"
    1.04
     hati
    0.98
     nak
    0.94
     jede
    0.93
     krat
    0.92
    有名な
    0.92
     NAT
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.