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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    20439
    -0.71
     constructor
    -0.68
    ãĤ´ãĥ³
    -0.68
    adelphia
    -0.64
    born
    -0.63
     fixme
    -0.62
     Thread
    -0.61
    alion
    -0.60
     Construct
    -0.60
     poop
    -0.60
    POSITIVE LOGITS
    anmar
    0.80
    Pac
    0.75
    umably
    0.70
    naissance
    0.69
    capital
    0.66
    idth
    0.65
     insiders
    0.65
     Hussein
    0.64
    behind
    0.62
    nces
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.