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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nude
    -0.72
    )=(
    -0.72
    phys
    -0.72
    kiss
    -0.70
     roast
    -0.69
    zee
    -0.66
    furt
    -0.66
     pies
    -0.65
    ãĥĨãĤ£
    -0.64
    sey
    -0.63
    POSITIVE LOGITS
     Receiver
    0.71
     Supporters
    0.69
    Reply
    0.69
     NCT
    0.68
    Critical
    0.67
     Anger
    0.67
    irlf
    0.64
     definitive
    0.64
    ATHER
    0.64
    impact
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.