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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hedral
    -0.69
    ogo
    -0.66
    alyst
    -0.65
    azon
    -0.60
    erest
    -0.59
    ulse
    -0.58
     appalled
    -0.57
    interested
    -0.57
    esthetic
    -0.57
     tastes
    -0.57
    POSITIVE LOGITS
    tainment
    0.73
    ãĤº
    0.72
    milo
    0.71
     Seym
    0.65
    neau
    0.64
    mere
    0.63
     Grac
    0.63
    tain
    0.62
     Firm
    0.62
     Ange
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.