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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .context
    -0.07
    看了一眼
    -0.07
    likes
    -0.07
    משפחה
    -0.07
     ככל
    -0.06
    以人为
    -0.06
    قاتل
    -0.06
    略
    -0.06
    普惠
    -0.06
    怜
    -0.06
    POSITIVE LOGITS
    isan
    0.08
    Non
    0.07
    KeyCode
    0.07
    AVED
    0.07
    Sections
    0.07
    Projects
    0.07
    regn
    0.07
     outright
    0.07
     Gauss
    0.07
    苦恼
    0.06
    Act Density 0.001%

    No Known Activations