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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    witz
    -0.73
    rill
    -0.70
    rium
    -0.70
     Vand
    -0.69
     McGill
    -0.68
     Syd
    -0.67
    ãĤ¦ãĤ¹
    -0.67
    cil
    -0.67
    istine
    -0.67
    kus
    -0.65
    POSITIVE LOGITS
     complicity
    0.73
     outsourcing
    0.68
    Closure
    0.67
    poke
    0.66
     unintended
    0.65
     largeDownload
    0.65
     surrog
    0.64
     adoption
    0.64
     royalty
    0.64
     compliance
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.