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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     retainer
    0.72
    オシャレ
    0.71
     freshest
    0.70
     picker
    0.68
     BOB
    0.66
    حت
    0.65
     duration
    0.64
    ម្បី
    0.64
    ج
    0.64
    кре
    0.63
    POSITIVE LOGITS
    he
    0.89
     Aank
    0.86
    Kid
    0.83
    wealth
    0.82
    amu
    0.81
    Leaders
    0.81
    Aula
    0.79
    aning
    0.79
    encija
    0.79
    Get
    0.78
    Act Density 0.001%

    No Known Activations