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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ilon
    -0.72
    aceutical
    -0.67
    ebus
    -0.65
     horizont
    -0.63
    erker
    -0.63
    icone
    -0.63
    omedical
    -0.62
    econom
    -0.61
    ioned
    -0.61
     Technician
    -0.61
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.74
     MSG
    0.68
    phant
    0.68
    cest
    0.68
    tz
    0.67
    tag
    0.65
    ãĥŀ
    0.65
     Zed
    0.64
     ts
    0.63
    tags
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.