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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    jos
    -0.08
    "/>
    -0.07
    capacity
    -0.07
    ｹ
    -0.07
    稳固
    -0.07
     doors
    -0.07
    r
    -0.07
    o
    -0.07
    	core
    -0.07
    *p
    -0.07
    POSITIVE LOGITS
    .what
    0.07
     moz
    0.07
    Negative
    0.07
     cộng
    0.07
     metav
    0.07
    (input
    0.07
    化妆品
    0.07
     irritating
    0.07
     yabancı
    0.06
     Levin
    0.06
    Act Density 0.081%

    No Known Activations