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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     censorship
    -0.69
     spam
    -0.69
    xx
    -0.65
     mob
    -0.64
    ffect
    -0.64
     backdoor
    -0.63
     interven
    -0.62
    oldown
    -0.61
    ction
    -0.60
    llah
    -0.60
    POSITIVE LOGITS
    Atl
    0.93
     Parables
    0.93
     Palest
    0.90
    angan
    0.72
    eport
    0.71
    FontSize
    0.70
     Orth
    0.69
     Catalan
    0.66
    vec
    0.66
    beit
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.