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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    1.02
    و
    1.00
     unver
    1.00
    в
    0.99
    0.98
    ハン
    0.97
    đ
    0.96
    Đ
    0.96
    o
    0.96
    égal
    0.95
    POSITIVE LOGITS
     timely
    1.33
     회
    1.32
     ancestry
    1.18
     lucha
    1.15
     pastry
    1.15
     homeopathy
    1.14
     Woolf
    1.14
     mantle
    1.12
     quota
    1.11
    𝐭
    1.11
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.