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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Large
    0.39
     For
    0.39
     Young
    0.38
     Younger
    0.37
      
    0.37
     Long
    0.36
     .
    0.36
     With
    0.36
     _
    0.34
     Slightly
    0.34
    POSITIVE LOGITS
     failings
    0.37
    istically
    0.36
     sanctity
    0.36
     mudanças
    0.35
     inequities
    0.35
     inefficiencies
    0.35
     semplici
    0.35
     semplice
    0.35
     injustices
    0.35
     insecurities
    0.34
    Act Density 0.668%

    No Known Activations