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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sentinel
    -0.07
    ises
    -0.07
    .mx
    -0.07
    自负
    -0.07
    一键
    -0.07
     Evangel
    -0.07
    inge
    -0.07
     inet
    -0.07
     Santiago
    -0.06
    utely
    -0.06
    POSITIVE LOGITS
     것이
    0.07
    年
    0.07
    'T
    0.07
     Буд
    0.06
    תחת
    0.06
    Have
    0.06
    polit
    0.06
    谇
    0.06
     가운데
    0.06
    严格的
    0.06
    Act Density 0.003%

    No Known Activations