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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hips
    -0.70
    ccoli
    -0.70
    asse
    -0.67
     Ezra
    -0.67
    cgi
    -0.67
    hide
    -0.64
     Polly
    -0.60
    dropping
    -0.59
     anything
    -0.59
     Akira
    -0.58
    POSITIVE LOGITS
     same
    0.81
     incumbent
    0.74
    retty
    0.67
    ĸļ
    0.67
     aftermath
    0.67
     simplicity
    0.66
     plight
    0.66
     seriousness
    0.66
    ta
    0.65
     complexity
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.