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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ubi
    -0.88
    sever
    -0.74
    pots
    -0.70
    notes
    -0.68
    aways
    -0.68
    wine
    -0.68
    ivably
    -0.68
    usb
    -0.67
    humans
    -0.67
    ichick
    -0.67
    POSITIVE LOGITS
     same
    1.02
     opposite
    0.85
     highest
    0.82
     lowest
    0.81
     latter
    0.76
     overall
    0.75
     extent
    0.73
     onset
    0.72
     average
    0.72
     remainder
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.