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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Bey
    -0.79
    LES
    -0.76
    views
    -0.75
     highs
    -0.75
    Pages
    -0.74
    ularity
    -0.74
    sets
    -0.74
    ãĥĭ
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.73
    gram
    -0.71
    POSITIVE LOGITS
     pension
    0.76
    iani
    0.75
     Cumm
    0.72
     treasurer
    0.71
    @#&
    0.69
     Pug
    0.68
     whisky
    0.66
     command
    0.63
     strugg
    0.61
    uberty
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.