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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     blaming
    0.63
     there
    0.62
     Liên
    0.61
     arguing
    0.59
     những
    0.59
    გომ
    0.59
     this
    0.58
     dealing
    0.57
    ಾಣ
    0.57
     shouting
    0.57
    POSITIVE LOGITS
     MUST
    0.73
     must
    0.68
     கண்டிப்பாக
    0.63
     can
    0.63
     میتوان
    0.62
     freely
    0.62
    用到
    0.62
    MUST
    0.61
    必须要
    0.60
     கொள்ளலாம்
    0.60
    Act Density 0.157%

    No Known Activations