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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    antasy
    -0.70
     Telecom
    -0.69
    eworks
    -0.68
    inance
    -0.67
    rock
    -0.65
    wark
    -0.64
    abad
    -0.63
    sey
    -0.63
    enance
    -0.63
     BELOW
    -0.62
    POSITIVE LOGITS
    artifacts
    0.87
     comr
    0.80
     perspect
    0.69
    EStream
    0.68
    yout
    0.66
     than
    0.66
     Vald
    0.65
     demonstrations
    0.64
     brig
    0.64
    reated
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.