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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iences
    -0.72
    chwitz
    -0.69
    leigh
    -0.68
    ilater
    -0.64
     upfront
    -0.64
     Ukrain
    -0.63
    iage
    -0.63
     Yose
    -0.62
     Rud
    -0.61
     Deity
    -0.60
    POSITIVE LOGITS
     ILCS
    0.75
     paraly
    0.69
     methyl
    0.68
     retina
    0.68
     paralysis
    0.65
    idine
    0.65
    ulic
    0.63
     PROG
    0.63
     violet
    0.62
    research
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.