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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     insert
    -0.64
    isphere
    -0.64
     obscure
    -0.63
     giveaways
    -0.63
     open
    -0.62
     Strauss
    -0.62
     unders
    -0.62
     honorable
    -0.61
     unintentionally
    -0.60
     digitally
    -0.60
    POSITIVE LOGITS
    serv
    0.72
    Cath
    0.72
    loe
    0.70
     Parish
    0.70
    atti
    0.70
     Patron
    0.70
    yon
    0.69
    onomy
    0.67
    regnancy
    0.66
    bil
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.