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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ignt
    -0.87
    xus
    -0.85
    ocene
    -0.85
    utical
    -0.83
     reflection
    -0.76
    iqueness
    -0.75
    aptic
    -0.74
    addin
    -0.73
    yip
    -0.73
    rored
    -0.72
    POSITIVE LOGITS
     broom
    0.66
     Paddock
    0.62
     beds
    0.62
     pots
    0.62
     fencing
    0.61
     ropes
    0.60
     cannabis
    0.60
     fare
    0.60
     barric
    0.60
     Spr
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.