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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tail
    0.54
    small
    0.53
    var
    0.51
    t
    0.51
    美味し
    0.48
    n
    0.48
    osm
    0.47
    teams
    0.46
     to
    0.46
    ergy
    0.45
    POSITIVE LOGITS
     തുറ
    0.53
     Rojas
    0.52
    кін
    0.50
    𝗔
    0.48
    🏪
    0.48
     leçon
    0.47
     questione
    0.47
    𝗟
    0.47
    🗯
    0.47
     сели
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.