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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pwr
    -0.71
     Bryant
    -0.69
     mole
    -0.67
    XY
    -0.65
    Ty
    -0.65
     squee
    -0.63
     Charm
    -0.62
    Jenn
    -0.62
     suspense
    -0.61
     disclaim
    -0.60
    POSITIVE LOGITS
    etsk
    0.89
    conservancy
    0.80
    gow
    0.76
    odynam
    0.76
    projects
    0.74
    assetsadobe
    0.73
    isphere
    0.72
    oulder
    0.70
    ament
    0.70
    glomer
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.