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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    am
    1.05
     všet
    1.03
     Stoke
    1.02
    며
    1.00
     boulder
    0.97
     وال
    0.97
    로
    0.96
    入住
    0.95
     HSM
    0.93
    Bathroom
    0.92
    POSITIVE LOGITS
    Ｔ
    1.34
    naive
    1.26
    年来
    1.25
    Ｙ
    1.23
    ulier
    1.21
    См
    1.19
     gsub
    1.18
     بڑے
    1.17
     idiot
    1.14
    निर
    1.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.