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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     opposite
    -0.08
    readcrumbs
    -0.07
    hest
    -0.07
     perpendicular
    -0.07
    ĺ
    -0.07
     telling
    -0.06
     cread
    -0.06
     guidelines
    -0.06
    opard
    -0.06
    -awesome
    -0.06
    POSITIVE LOGITS
    뜨
    0.08
     amplified
    0.08
    녓
    0.07
     im
    0.07
    IGNAL
    0.07
     Giriş
    0.07
     parade
    0.07
    셒
    0.07
    乔
    0.07
    .isfile
    0.06
    Act Density 0.022%

    No Known Activations