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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     resigned
    -0.07
     ai
    -0.07
    人身
    -0.07
     EntryPoint
    -0.07
    反击
    -0.07
     enough
    -0.07
    },
↵
    -0.07
    ture
    -0.07
     перемен
    -0.07
     dispatch
    -0.06
    POSITIVE LOGITS
    faq
    0.07
    𝕕
    0.06
     Neue
    0.06
    >Last
    0.06
    定期
    0.06
    CTL
    0.06
    -messages
    0.06
    ユ
    0.06
    quence
    0.06
     porém
    0.06
    Act Density 0.062%

    No Known Activations