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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    artisan
    -0.72
    mand
    -0.72
    esters
    -0.65
    otyp
    -0.64
     orally
    -0.63
    owsky
    -0.61
    osate
    -0.60
    itudinal
    -0.60
    enei
    -0.60
     Written
    -0.59
    POSITIVE LOGITS
    ITNESS
    0.69
     Bauer
    0.66
    here
    0.66
    ité
    0.66
    isons
    0.66
    illac
    0.65
    iliary
    0.64
    illon
    0.64
     Marqu
    0.63
    ÃŁ
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.