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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Frie
    -0.95
     unbeliev
    -0.91
    ahon
    -0.76
    yout
    -0.76
     paran
    -0.75
     Afgh
    -0.70
    psey
    -0.70
     proport
    -0.70
     tradem
    -0.69
    Ħ¢
    -0.67
    POSITIVE LOGITS
    ights
    0.70
    ER
    0.70
    sing
    0.69
    ÃŃ
    0.69
    rast
    0.68
    ESS
    0.67
    izations
    0.66
    CHO
    0.66
    Ö
    0.66
    âĢİ
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.