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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mys
    -0.69
     library
    -0.67
    inguished
    -0.66
     reperto
    -0.65
    rer
    -0.65
     backlog
    -0.61
     rave
    -0.61
    ync
    -0.61
    heid
    -0.60
    rentice
    -0.60
    POSITIVE LOGITS
    ModLoader
    0.75
    é¾įå
    0.73
    Ļ½
    0.68
    çļ
    0.68
    ãĤ¨ãĥ«
    0.66
     Lauder
    0.65
     LX
    0.62
    aways
    0.61
    £ı
    0.60
    éŃĶ
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.