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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cer
    -0.70
     highs
    -0.66
    riz
    -0.64
     pubs
    -0.62
    icides
    -0.60
     Blizzard
    -0.60
     cess
    -0.60
    cers
    -0.59
     ic
    -0.59
    rier
    -0.58
    POSITIVE LOGITS
    sonian
    0.90
    arta
    0.80
    ÅŁ
    0.76
    hift
    0.75
    untu
    0.73
    uthor
    0.73
    Å¡
    0.71
    hedon
    0.70
     arrang
    0.69
     pilgr
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.