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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    FACE
    -0.75
    éĥ
    -0.75
    GROUP
    -0.69
    ãĥ³ãĤ¸
    -0.69
    cu
    -0.67
    igrants
    -0.66
    ãĥ¼ãĥĨ
    -0.65
    ities
    -0.65
    kson
    -0.64
    æĺ
    -0.64
    POSITIVE LOGITS
    ocative
    0.69
    ipop
    0.68
    apo
    0.65
    alos
    0.65
    eanor
    0.64
    orem
    0.64
     err
    0.63
    alla
    0.62
    urance
    0.62
    asive
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.