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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     to
    0.54
    tail
    0.53
    t
    0.52
    n
    0.52
    small
    0.51
    人
    0.50
     Waring
    0.47
    is
    0.46
    ergy
    0.46
    美味し
    0.46
    POSITIVE LOGITS
    🏪
    0.55
    𝗔
    0.55
    кін
    0.54
    💲
    0.53
    𝗟
    0.53
    𝑰
    0.52
     തുറ
    0.51
    𝗘
    0.51
     сели
    0.51
    🏤
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.