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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oka
    -0.74
    cia
    -0.74
    ante
    -0.73
    uga
    -0.71
     Tata
    -0.70
    eka
    -0.67
     Lanka
    -0.65
     Sense
    -0.64
     Gohan
    -0.62
     Io
    -0.62
    POSITIVE LOGITS
    ovember
    0.78
    blance
    0.76
    tenance
    0.72
    axies
    0.72
     envy
    0.70
    mbuds
    0.69
    ledge
    0.68
     dow
    0.66
     wardrobe
    0.66
     salon
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.