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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     brave
    -0.07
    倒塌
    -0.07
    כנו
    -0.07
     Monday
    -0.06
     baby
    -0.06
     buena
    -0.06
     flowing
    -0.06
     dog
    -0.06
     recommendation
    -0.06
     CAL
    -0.06
    POSITIVE LOGITS
    美学
    0.07
    伊斯
    0.07
    轨道
    0.06
     patter
    0.06
    表白
    0.06
    悢
    0.06
    杼
    0.06
    ทรา
    0.06
    ød
    0.06
     '"';↵
    0.06
    Act Density 0.001%

    No Known Activations