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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    roxy
    -0.91
    ibaba
    -0.84
    ruits
    -0.76
    Downloadha
    -0.75
    renheit
    -0.74
    rious
    -0.74
    mares
    -0.72
    rontal
    -0.72
    udos
    -0.70
    rices
    -0.70
    POSITIVE LOGITS
    athe
    0.67
    iege
    0.63
     cry
    0.63
     Warden
    0.62
    esan
    0.61
    eteria
    0.61
     reformed
    0.60
     stamp
    0.60
     imprisonment
    0.58
     apartheid
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.