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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    2
    -0.08
     undo
    -0.08
    4
    -0.08
    on
    -0.07
    ego
    -0.07
    biology
    -0.07
    LOOK
    -0.07
    nn
    -0.07
     Extr
    -0.07
    3
    -0.07
    POSITIVE LOGITS
     machine
    0.10
    机
    0.09
    .OrderBy
    0.08
    .machine
    0.08
     MACHINE
    0.08
     имеет
    0.07
     machines
    0.07
    每个人都
    0.07
     trochę
    0.07
     Machines
    0.07
    Act Density 0.029%

    No Known Activations