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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ¹
    -0.80
    ãĥĺãĥ©
    -0.78
    enta
    -0.75
    origin
    -0.74
    bard
    -0.73
    ãĥİ
    -0.73
    latable
    -0.73
    atan
    -0.73
    ornia
    -0.72
    xy
    -0.72
    POSITIVE LOGITS
     gearing
    0.78
     trou
    0.73
     pipelines
    0.70
     triv
    0.65
     grading
    0.64
     TCU
    0.64
     disadvant
    0.64
     consecut
    0.63
     exce
    0.63
     Griff
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.