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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     satisfaction
    -0.67
    Sov
    -0.66
     bye
    -0.65
    ãģ§
    -0.65
    ural
    -0.64
     Buk
    -0.61
    ritis
    -0.60
     Juliet
    -0.59
    Ko
    -0.59
     enjoyment
    -0.59
    POSITIVE LOGITS
    ardless
    0.73
    ettes
    0.71
    engers
    0.68
     Surge
    0.67
    ittal
    0.64
     Granger
    0.64
    ogle
    0.62
    atility
    0.62
    aban
    0.61
    ogue
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.