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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    인
    0.54
    Да
    0.54
    <0x0D>
    0.53
    네
    0.53
    买
    0.52
    Я
    0.51
    페
    0.50
    К
    0.50
    Ин
    0.50
    客様
    0.50
    POSITIVE LOGITS
     refusal
    0.47
    Ꮔ
    0.46
     aik
    0.45
    मुक्त
    0.45
     dosing
    0.43
     TMZ
    0.43
     membuka
    0.43
     complet
    0.43
     နှစ်
    0.43
     anorexia
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.