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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tre
    -0.70
    etting
    -0.69
    ãĤ·ãĥ£
    -0.66
    Tre
    -0.64
    ista
    -0.63
     ted
    -0.62
     sorcery
    -0.62
    udi
    -0.60
     past
    -0.59
     pleasures
    -0.59
    POSITIVE LOGITS
    hatt
    0.86
    vertisement
    0.72
     Jackets
    0.71
    hirt
    0.70
    henko
    0.67
     uniform
    0.66
    uberty
    0.66
    auld
    0.65
    andowski
    0.65
     teasp
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.