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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lauded
    0.95
     lessened
    0.85
     ভীষণ
    0.83
     famed
    0.82
     supremely
    0.80
     हेतु
    0.80
     enthr
    0.79
     comfy
    0.78
     weaponry
    0.78
     sizeable
    0.77
    POSITIVE LOGITS
    ���
    0.64
    0.62
    ^
    0.61
    <unused2221>
    0.60
     Algunas
    0.60
    ánd
    0.58
    <eos>
    0.57
    \
    0.57
    ô
    0.57
     μπορεί
    0.57
    Act Density 0.599%

    No Known Activations