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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Wild
    -0.08
    xe
    -0.07
     Vulkan
    -0.07
    孔雀
    -0.07
    (*
    -0.07
    Beam
    -0.07
    osen
    -0.07
     Wild
    -0.06
    嗞
    -0.06
     cooked
    -0.06
    POSITIVE LOGITS
    调研
    0.08
     MULT
    0.08
     pertinent
    0.07
     fid
    0.07
    *j
    0.07
     Associate
    0.07
     OTP
    0.07
    相识
    0.07
     Zhou
    0.07
     crime
    0.07
    Act Density 0.337%

    No Known Activations