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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ
    -0.76
    CLUS
    -0.74
    iqueness
    -0.67
    DEN
    -0.67
    pants
    -0.66
    tek
    -0.66
    drops
    -0.65
    krit
    -0.65
    èĢ
    -0.64
    washed
    -0.64
    POSITIVE LOGITS
    ophon
    0.85
    uyomi
    0.83
    arios
    0.68
    xiety
    0.67
    soever
    0.67
    och
    0.64
     Tribune
    0.62
     maneu
    0.61
    uckland
    0.61
    estial
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.