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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sne
    -0.08
    手游
    -0.08
    SELF
    -0.07
    感冒
    -0.07
     �
    -0.07
    _APP
    -0.07
    SO
    -0.07
    росс
    -0.07
    thinkable
    -0.07
    סור
    -0.07
    POSITIVE LOGITS
     #:
    0.07
    hawks
    0.07
     cbd
    0.06
     distracting
    0.06
     need
    0.06
     أهم
    0.06
    icopt
    0.06
    OU
    0.06
    好几个
    0.06
    layui
    0.06
    Act Density 0.007%

    No Known Activations