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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bulls
    -0.75
    ukes
    -0.68
    jab
    -0.67
    urers
    -0.66
    uke
    -0.66
    holder
    -0.65
    mun
    -0.64
    mong
    -0.63
     backpack
    -0.63
     pool
    -0.62
    POSITIVE LOGITS
    âĸij
    0.82
     guiActive
    0.76
     Stain
    0.75
    ÃĥÃĤ
    0.74
     Tune
    0.73
     Slay
    0.72
     Showtime
    0.72
    artney
    0.72
    âĸijâĸij
    0.71
     Dign
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.