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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     attentive
    -0.07
     Charlotte
    -0.07
     kind
    -0.07
    🐱
    -0.07
    码头
    -0.06
     JMP
    -0.06
     IG
    -0.06
    modes
    -0.06
    致富
    -0.06
    -store
    -0.06
    POSITIVE LOGITS
    PageRoute
    0.07
    ecause
    0.07
    公共
    0.07
    )?$
    0.07
    _exchange
    0.06
     FIXED
    0.06
    .Angle
    0.06
    arefa
    0.06
     świecie
    0.06
    wendung
    0.06
    Act Density 0.001%

    No Known Activations