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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Summer
    -0.08
    一个新的
    -0.07
    iol
    -0.07
    Microsoft
    -0.07
     Telegram
    -0.06
    Donald
    -0.06
    perc
    -0.06
     conglomer
    -0.06
    _MODEL
    -0.06
    andFilterWhere
    -0.06
    POSITIVE LOGITS
    -threat
    0.07
    练习
    0.07
    _jet
    0.07
    ракти
    0.07
     recruit
    0.07
    的压力
    0.07
    .SUB
    0.07
     arriv
    0.07
    特质
    0.07
    否則
    0.06
    Act Density 0.035%

    No Known Activations